Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-2-2B
0-GEMMASCOPE-TRANSCODER-16K
7138
Prev
Next
MODEL
0-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
the word 'meaning', sometimes with related words
oai_token-act-pair · gemini-2.0-flash
No Scores
meaning
np_max-act · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
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.0.ln2.hook_normalized
Architecture
jumprelu_transcoder
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/0-gemmascope-transcoder-16k/7138?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/0-gemmascope-transcoder-16k/7138?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
.
-0.85
,
-0.74
vs
-0.71
!
-0.68
↵↵
-0.67
-
-0.67
/
-0.66
-
-0.65
(
-0.65
(
-0.60
POSITIVE LOGITS
NUMX
1.44
―――――
1.39
myſelf
1.34
itſelf
1.28
iſt
1.23
་་
1.20
ſind
1.18
ſelf
1.17
leſs
1.16
Egli
1.16
Act
ivations
Density 1.880%
Test
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
