© 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. 917
    Prev
    Next
    INDEX
    Explanations

    questions asking for somebody's opinion or thoughts

    oai_token-act-pair · gemini-2.0-flash

    think

    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
     clearly
    -0.93
    Datuak
    -0.83
    AsUp
    -0.83
    parsedMessage
    -0.81
     Clearly
    -0.78
    enumi
    -0.77
    Clearly
    -0.76
     values
    -0.76
    clearly
    -0.73
    脚注の使い方
    -0.71
    POSITIVE LOGITS
    новништво
    0.59
    CodeAttribute
    0.57
    ftagPool
    0.54
    olfen
    0.53
     néz
    0.48
    Expensive
    0.48
    WriteAttribute
    0.48
    expensive
    0.46
    ILITY
    0.46
     شام
    0.45
    Activations Density 13.176%

    No Known Activations