© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1567
    Prev
    Next
    INDEX
    Explanations

    words related to crimes, politics, and the justice system

    oai_token-act-pair · gemini-2.0-flash

    Legal issues, investigations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    rst
    -0.49
    itivo
    -0.47
    רְ
    -0.47
    ʁ
    -0.46
     élas
    -0.45
     musiciens
    -0.44
    ="//
    -0.42
     الرياضيه
    -0.42
    raga
    -0.42
    ️
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.91
    CloseOperation
    0.85
    Ecotoxicity
    0.79
     ویکی‌پدیای
    0.75
    LookAnd
    0.72
     Roskov
    0.72
    featureID
    0.67
    GEBURTSDATUM
    0.65
    IntoConstraints
    0.65
    AnchorStyles
    0.65
    Activations Density 5.392%

    No Known Activations