© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4672
    Prev
    Next
    INDEX
    Explanations

    words related to laws, rules and breaking them.

    oai_token-act-pair · gemini-2.0-flash

    Violations and non-compliance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ainfi
    -0.70
    tagHelperRunner
    -0.68
    ReusableCell
    -0.67
     alimentaire
    -0.65
     vendus
    -0.65
     tdci
    -0.65
     devenus
    -0.65
     conseguenza
    -0.64
     cdti
    -0.63
    writeField
    -0.63
    POSITIVE LOGITS
     safety
    0.63
     cap
    0.56
     local
    0.54
     Safety
    0.53
     fan
    0.52
     Nor
    0.50
     referenties
    0.50
    shid
    0.50
    mander
    0.50
     Trump
    0.49
    Activations Density 14.418%

    No Known Activations