© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12368
    Prev
    Next
    INDEX
    Explanations

    mentions of legal procedures and attempts to formulate them as questions

    oai_token-act-pair · gemini-2.0-flash

    Legal/geopolitical context

    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
    RenderAtEndOf
    -0.88
    modb
    -0.76
     ModelExpression
    -0.76
     становника
    -0.73
    PyExc
    -0.73
    AnimationsModule
    -0.71
    Према
    -0.70
    GEBURTSDATUM
    -0.70
     незавершена
    -0.69
    PerformLayout
    -0.68
    POSITIVE LOGITS
    NECT
    0.46
    pos
    0.42
     Säure
    0.41
    acide
    0.40
    ССР
    0.40
    F
    0.39
    ratos
    0.39
     szab
    0.39
    ens
    0.39
     Kläger
    0.39
    Activations Density 1.191%

    No Known Activations