© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9488
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases common to legal documents and opinions

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

    np_token-act-pair-logits · gpt-4o-mini

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    rawQuery
    -0.52
     simplifié
    -0.51
    DropTable
    -0.50
    abestanden
    -0.49
    ‍♀
    -0.47
    amoan
    -0.47
    VersionUID
    -0.45
     AssemblyTitle
    -0.44
     TextInputType
    -0.43
     <<=
    -0.43
    POSITIVE LOGITS
     oprot
    0.85
    ViewFeatures
    0.70
    fromnode
    0.69
    rungsseite
    0.67
     cherchés
    0.61
    клопе
    0.60
    tonode
    0.59
    ConstraintMaker
    0.59
    vrigt
    0.56
    BeginInit
    0.54
    Activations Density 2.502%

    No Known Activations