© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13986
    Prev
    Next
    INDEX
    Explanations

    text discussing medical treatments and diseases

    oai_token-act-pair · gemini-2.0-flash

    antibiotics and medicine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    -------------</
    -0.52
     وتسجيلات
    -0.50
     للاسماء
    -0.49
    :✨
    -0.48
     opérés
    -0.46
    reportWebVitals
    -0.45
     requestCode
    -0.45
     CURIAM
    -0.45
    AlterField
    -0.44
     Nauk
    -0.44
    POSITIVE LOGITS
    例文帳に追加
    0.68
    afficheront
    0.56
    liage
    0.54
    %")
    0.53
     IMA
    0.53
     bed
    0.52
    '])){
    0.50
     panting
    0.50
     handleMessage
    0.49
    izations
    0.49
    Activations Density 3.380%

    No Known Activations