© 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. 39845
    Prev
    Next
    INDEX
    Explanations

    dude girl ho

    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
    s
    0.95
    r
    0.82
    il
    0.79
    y
    0.77
    ों
    0.73
    ی
    0.73
    f
    0.70
    ó
    0.66
    க்
    0.66
    م
    0.66
    POSITIVE LOGITS
    の前
    0.61
    MenuItem
    0.57
    chenk
    0.56
    見える
    0.55
     DISEASE
    0.54
    お届け
    0.54
     불구하고
    0.54
    பிர
    0.53
    kenalkan
    0.52
     xhrObj
    0.52
    Activations Density 0.003%

    No Known Activations