Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-2-2B
2-GEMMASCOPE-TRANSCODER-16K
14213
Prev
Next
MODEL
2-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
technical or scientific terms related to chemistry, biology or mathematics
oai_token-act-pair · 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_2/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/2-gemmascope-transcoder-16k/14213?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/2-gemmascope-transcoder-16k/14213?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
-0.85
,
-0.82
"
-0.79
N
-0.73
e
-0.71
'
-0.71
'
-0.70
"
-0.69
M
-0.68
“
-0.67
POSITIVE LOGITS
Efq
1.66
Monfieur
1.47
myſelf
1.46
itſelf
1.44
Jefus
1.44
DockStyle
1.39
Majefty
1.35
ſelf
1.34
Reſ
1.33
мәкал
1.32
Act
ivations
Density 0.503%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
