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
25-GEMMASCOPE-TRANSCODER-16K
1746
Prev
Next
MODEL
25-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
genetic sequences
oai_token-act-pair · gemini-2.0-flash
No Scores
gene bHLH
np_max-act-logits · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope/layer_25/width_16k
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/25-gemmascope-transcoder-16k/1746?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/25-gemmascope-transcoder-16k/1746?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
H
-0.66
HA
-0.58
h
-0.55
referenties
-0.52
һ
-0.52
ฮ
-0.50
Roskov
-0.50
HB
-0.50
Hn
-0.50
HH
-0.49
POSITIVE LOGITS
hin
0.84
her
0.83
hon
0.82
his
0.81
ha
0.81
hs
0.80
hos
0.79
hing
0.79
han
0.78
has
0.77
Act
ivations
Density 12.078%
Test
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
