© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13668
    Prev
    Next
    INDEX
    Explanations

    words associated with drug use, drug sales, and the legal system that combats them

    oai_token-act-pair · gemini-2.0-flash

    drug

    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
     drug
    -2.14
     Drug
    -1.99
     drugs
    -1.88
    Drug
    -1.84
    drug
    -1.80
     Drugs
    -1.73
     DRUG
    -1.68
    Drugs
    -1.63
    drugs
    -1.58
     drogas
    -1.23
    POSITIVE LOGITS
     dAtA
    0.63
    HomeAsUpEnabled
    0.62
     FetchType
    0.62
    __*/
    0.58
    VolleyError
    0.57
    skjaer
    0.57
    CloseOperation
    0.57
    ArrowToggle
    0.55
     cooker
    0.53
    AddTagHelper
    0.53
    Activations Density 4.295%

    No Known Activations