© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8090
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies or experiment results

    oai_token-act-pair · gemini-2.0-flash

    foreign user identification words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     quartos
    -0.34
    ッチ
    -0.32
     Popis
    -0.32
     alternates
    -0.30
     abuse
    -0.30
     подойдет
    -0.30
     coelho
    -0.29
     alternation
    -0.29
     carbons
    -0.29
     overla
    -0.29
    POSITIVE LOGITS
     يتيمه
    1.11
     ModelExpression
    1.06
    出版年
    0.99
     חיצוניים
    0.97
    findpost
    0.97
     autorytatywna
    0.96
     Exactos
    0.94
    Personensuche
    0.93
     nakalista
    0.91
    Personendaten
    0.91
    Activations Density 9.334%

    No Known Activations