© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133643
    Prev
    Next
    INDEX
    Explanations

    driving

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     drunken
    1.23
     drunk
    1.22
     drunkenness
    1.15
    醉
    1.12
    drunk
    1.09
    酔
    1.01
    喝
    0.91
    酩
    0.87
     नशे
    0.85
    runken
    0.84
    POSITIVE LOGITS
    TIM
    0.37
     slides
    0.36
     allá
    0.36
     slid
    0.36
    Low
    0.34
     andolan
    0.34
    Slides
    0.34
     undeveloped
    0.34
     Cesare
    0.33
    ifolia
    0.33
    Activations Density 0.006%

    No Known Activations