© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127938
    Prev
    Next
    INDEX
    Explanations

    slapstick humor

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    F
    0.84
    am
    0.82
    UR
    0.81
    AK
    0.79
    on
    0.77
    HQ
    0.71
    RI
    0.68
    AI
    0.68
    GUI
    0.65
    UO
    0.65
    POSITIVE LOGITS
    ח
    0.77
    ва
    0.70
    ः
    0.69
    dt
    0.68
    ן
    0.68
     اک
    0.64
    {};
    0.64
     автомобиля
    0.64
     заседа
    0.64
     различи
    0.63
    Activations Density 0.000%

    No Known Activations