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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7000
    Prev
    Next
    INDEX
    Explanations

    quoted legal text

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating quotation or reference

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

    Formal writing snippets

    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
    AnimationsModule
    -0.77
    帖最后由
    -0.73
    uxxxx
    -0.73
    Varint
    -0.69
    UrlResolution
    -0.69
    ImageContext
    -0.69
    antren
    -0.68
    ływ
    -0.68
    تقاوى
    -0.68
    URLException
    -0.67
    POSITIVE LOGITS
     ahol
    0.40
    انظر
    0.40
    See
    0.39
     kø
    0.38
    itom
    0.38
     dalamnya
    0.38
    here
    0.36
    ‌است
    0.36
    ver
    0.36
     See
    0.36
    Activations Density 3.941%

    No Known Activations