© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3917
    Prev
    Next
    INDEX
    Explanations

    JSON-like responses containing the words "success" and "message", as well as instances of the words "has", "been", and "in"

    oai_token-act-pair · gemini-2.0-flash

    True

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    対
    -0.38
    ?
    -0.38
    たい
    -0.38
     Beratung
    -0.38
    ...
    -0.38
        
    -0.38
    arh
    -0.37
    Sco
    -0.36
     swe
    -0.36
    TO
    -0.36
    POSITIVE LOGITS
     Мексичка
    0.81
    Personendaten
    0.79
    principalColumn
    0.79
    addPreferredGap
    0.76
    حياتها
    0.75
    fillType
    0.74
     يتيمه
    0.71
     كومونز
    0.69
    AlterField
    0.69
    <bos>
    0.69
    Activations Density 31.216%

    No Known Activations