© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5686
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to software and app development

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or specific terms related to development

    np_token-act-pair-logits · gpt-4o-mini

    app/service development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    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
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.73
    aarrggbb
    -0.72
    IntoConstraints
    -0.68
     skolan
    -0.65
     виправивши
    -0.65
    จึง
    -0.62
    tôi
    -0.61
    )‏
    -0.61
     Theſe
    -0.60
    lgari
    -0.58
    POSITIVE LOGITS
    mtd
    0.51
    شه
    0.47
    routeProvider
    0.47
    SMO
    0.47
     pré
    0.47
    INGHAM
    0.45
    ismet
    0.44
    новништво
    0.44
    wid
    0.43
    advertisement
    0.42
    Activations Density 5.639%

    No Known Activations