© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5638
    Prev
    Next
    INDEX
    Explanations

    code snippets, possibly from multiple languages, containing keywords like "if", "else", function names, and tags

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CascadeType
    -0.47
     Eman
    -0.46
     reared
    -0.44
    ुष
    -0.44
     Piles
    -0.43
     Aze
    -0.43
    motors
    -0.42
     brack
    -0.42
    ømme
    -0.42
     catalyzed
    -0.41
    POSITIVE LOGITS
    WebVitals
    0.75
    RenderAtEndOf
    0.70
    elle
    0.68
    UpInside
    0.68
     незавершена
    0.67
    endif
    0.66
    出版年
    0.66
    Хьажоргаш
    0.65
    el
    0.65
    else
    0.64
    Activations Density 4.978%

    No Known Activations