© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10298
    Prev
    Next
    INDEX
    Explanations

    Latex-formatted math formulas enclosed in brackets or braces

    oai_token-act-pair · gemini-2.0-flash

    bracket

    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
    joo
    -0.46
    ExecuteReader
    -0.41
    терапия
    -0.41
    ficulties
    -0.40
     titular
    -0.40
    LocalizedString
    -0.40
    ereza
    -0.40
    asgi
    -0.39
     『
    -0.39
     zor
    -0.39
    POSITIVE LOGITS
    <bos>
    1.73
     समीक्षक
    0.82
     AssemblyTitle
    0.80
    QMetaType
    0.77
    __':
    0.77
    ⓧ
    0.73
     nahilalakip
    0.69
    MLLoader
    0.69
     />\
    0.69
    '},
    0.68
    Activations Density 0.493%

    No Known Activations