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
1579
Prev
Next
MODEL
25-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
code snippets including XML tags and references to UI elements
oai_token-act-pair · gemini-2.0-flash
No Scores
animal
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/1579?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/1579?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
}>
-1.55
]>
-1.39
}}>
-1.38
)}>
-1.37
'>
-1.35
)>
-1.29
}>
-1.27
}}>
-1.25
>
-1.23
">
-1.21
POSITIVE LOGITS
animal
1.68
animal
1.54
Animal
1.52
Animal
1.49
ANIMAL
1.46
ANIMAL
1.46
animals
1.38
Animals
1.31
Animals
1.29
animals
1.21
Act
ivations
Density 1.367%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations