© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2170
    Prev
    Next
    INDEX
    Explanations

    capitalized abbreviations, names associated with the Maori, and words that might be fragments of labels in code

    oai_token-act-pair · gemini-2.0-flash

    Po

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     po
    -1.91
     Po
    -1.88
    Po
    -1.82
    po
    -1.61
     PO
    -1.60
    PO
    -1.52
     pos
    -1.31
    pos
    -1.30
     POS
    -1.29
     Pos
    -1.26
    POSITIVE LOGITS
     كومونز
    0.82
    DebuggerNonUser
    0.72
    CppMethod
    0.67
    StoryboardSegue
    0.64
    $.}
    0.60
     Проци
    0.59
    interopRequire
    0.57
    RenderAtEndOf
    0.57
    Kanpo
    0.56
    外部リンク
    0.55
    Activations Density 10.437%

    No Known Activations