© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8772
    Prev
    Next
    INDEX
    Explanations

    words relating to legal procedures, administration, organization and regulation.

    oai_token-act-pair · gemini-2.0-flash

    official scenarios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     hoved
    -0.47
    Халык
    -0.45
    //</
    -0.42
     daqui
    -0.42
     Visions
    -0.41
     tamamen
    -0.39
    ->_
    -0.39
     Prison
    -0.37
     elettrica
    -0.37
    moc
    -0.37
    POSITIVE LOGITS
     مشين
    0.72
    testng
    0.72
     跳转至
    0.71
    tanleria
    0.69
    WebVitals
    0.68
     שוליים
    0.67
    djangoproject
    0.65
     utafitiHapana
    0.64
    UserScript
    0.62
    InSection
    0.61
    Activations Density 2.870%

    No Known Activations