© 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. 47182
    Prev
    Next
    INDEX
    Explanations

    ends with -um, -on, -as, -ov, -aur, -os

    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
    IS
    0.75
     Nizam
    0.67
    ป
    0.66
     Nawab
    0.64
    Y
    0.63
     Bant
    0.63
     Stadion
    0.62
     as
    0.62
     Todor
    0.62
     Tohoku
    0.62
    POSITIVE LOGITS
    на
    0.91
    ся
    0.89
    -
    0.85
    al
    0.81
     is
    0.75
    ai
    0.69
    fts
    0.69
    ρα
    0.68
    ł
    0.68
     has
    0.66
    Activations Density 0.000%

    No Known Activations