© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192345
    Prev
    Next
    INDEX
    Explanations

    ending of words like 'ance' or Spanish suffixes

    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_4_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
    л
    1.14
    י
    1.03
     of
    1.00
    ו
    0.98
     seguito
    0.89
    ক
    0.85
     on
    0.83
    ล
    0.82
     był
    0.78
    ব
    0.76
    POSITIVE LOGITS
    om
    1.20
    for
    1.14
    m
    1.09
    t
    1.03
    aj
    0.96
    me
    0.93
    ana
    0.91
    od
    0.89
    g
    0.89
    ag
    0.88
    Activations Density 0.019%

    No Known Activations