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
21-GEMMASCOPE-TRANSCODER-16K
5730
Prev
Next
MODEL
21-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
words around the preposition 'at' and words related to attempts/effort
oai_token-act-pair · gemini-2.0-flash
No Scores
tokens related to context and conversation
np_token-act-pair-logits · gpt-4o-mini
No Scores
mixed text contexts
np_max-act-logits · 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_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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/21-gemmascope-transcoder-16k/5730?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/21-gemmascope-transcoder-16k/5730?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
itſelf
-1.45
myſelf
-1.33
raiſ
-1.26
་་
-1.26
Efq
-1.23
pleaſure
-1.23
ſche
-1.23
ſind
-1.23
auffi
-1.19
faſt
-1.19
POSITIVE LOGITS
0.88
$
0.82
"
0.79
$\
0.79
c
0.77
x
0.74
“
0.71
a
0.69
<eos>
0.69
b
0.69
Act
ivations
Density 5.244%
Test
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
