© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135281
    Prev
    Next
    INDEX
    Explanations

    words ending in ish or similar

    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_6_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
     is
    0.85
     p
    0.72
     and
    0.72
    uja
    0.71
     I
    0.70
     Python
    0.70
    ur
    0.70
     final
    0.70
     not
    0.69
     Alzheimer
    0.69
    POSITIVE LOGITS
    ль
    1.04
    Бы
    1.02
    л
    1.02
    な
    0.99
    Ф
    0.99
    ની
    0.98
    ス
    0.96
    П
    0.96
    分钟
    0.93
    ル
    0.92
    Activations Density 0.000%

    No Known Activations