© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Gemma-2-2B
21-GEMMASCOPE-TRANSCODER-16K
14974
Prev
Next
MODEL
21-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
mathematical notation and equations
oai_token-act-pair · gemini-2.0-flash
No Scores
special characters and mathematical syntax
np_token-act-pair-logits · gpt-4o-mini
No Scores
-
np_max-act-logits · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.21.ln2.hook_normalized
Architecture
jumprelu_transcoder
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-2b/21-gemmascope-transcoder-16k/14974?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/21-gemmascope-transcoder-16k/14974?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
-
-1.52
–
-1.49
–
-1.40
−
-1.24
−
-1.19
—
-1.18
--
-1.15
－
-1.09
-\
-1.00
—
-0.99
POSITIVE LOGITS
itſelf
0.77
:')
0.68
:");
0.68
greateſt
0.68
Jurí
0.68
་་
0.68
IVEREF
0.67
IonicModule
0.66
!")
0.66
doubtnut
0.65
Act
ivations
Density 2.657%
Test
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
