© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10747
    Prev
    Next
    INDEX
    Explanations

    words or symbols associated with biochemistry research papers

    oai_token-act-pair · gemini-2.0-flash

    Predictions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    sizeCache
    -0.91
    ValueStyle
    -0.90
    AccessorTable
    -0.87
    parsedMessage
    -0.85
    WireFormatLite
    -0.81
     tartalomajánló
    -0.80
    ècie
    -0.79
    protoimpl
    -0.78
     كومونز
    -0.77
     للمعارف
    -0.76
    POSITIVE LOGITS
     prediction
    0.56
     predictions
    0.52
     predict
    0.48
     Prediction
    0.45
    predictions
    0.44
    prediction
    0.43
     predicting
    0.43
    pf
    0.40
    P
    0.39
    预测
    0.38
    Activations Density 3.467%

    No Known Activations