© 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. 232791
    Prev
    Next
    INDEX
    Explanations

    whole grains or wheat

    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
    ם
    1.00
    س
    0.95
    RENCE
    0.83
    ()\
    0.81
    нг
    0.79
    сел
    0.78
     sơn
    0.78
     arbres
    0.78
    сить
    0.77
    ۰
    0.77
    POSITIVE LOGITS
    ed
    1.48
    i
    1.17
    er
    1.13
    e
    1.01
    ي
    1.01
    he
    1.00
    in
    0.95
    on
    0.93
    a
    0.93
    el
    0.92
    Activations Density 0.002%

    No Known Activations