© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1580
    Prev
    Next
    INDEX
    Explanations

    words associated with law, crime, drugs, and legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    drug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     drug
    -2.05
     drugs
    -1.88
     Drug
    -1.87
    Drug
    -1.73
     Drugs
    -1.70
    drug
    -1.66
     DRUG
    -1.64
    Drugs
    -1.62
    drugs
    -1.56
    药物
    -1.37
    POSITIVE LOGITS
     resourceCulture
    0.56
    MLLoader
    0.55
     claro
    0.54
    picable
    0.53
    gameserver
    0.52
     MessageBoxIcon
    0.52
    ptonshire
    0.50
    躇
    0.50
    Sprintf
    0.50
     Washable
    0.50
    Activations Density 12.869%

    No Known Activations