© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13433
    Prev
    Next
    INDEX
    Explanations

    crack cocaine and its base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    찍
    0.50
    "
    0.49
     aquel
    0.48
     GIS
    0.47
     endDate
    0.47
     indispens
    0.46
     tarot
    0.46
     dapp
    0.46
     SUN
    0.45
     prolog
    0.45
    POSITIVE LOGITS
    newlines
    0.57
    thew
    0.54
    it
    0.51
    itm
    0.50
    améliorer
    0.50
    ;\
    0.50
    achte
    0.50
    fta
    0.49
    latin
    0.48
    holy
    0.48
    Activations Density 0.023%

    No Known Activations