© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156456
    Prev
    Next
    INDEX
    Explanations

    Zeeland, zygote, Zepto

    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_2_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
    وم
    1.09
    üd
    1.03
    る
    1.00
    AA
    0.98
    ير
    0.97
    りと
    0.97
    고
    0.95
    ম্প
    0.95
    ON
    0.94
    يل
    0.94
    POSITIVE LOGITS
    ص
    1.85
    er
    1.60
    p
    1.46
    in
    1.44
    s
    1.42
    i
    1.41
    ,
    1.39
    that
    1.30
    v
    1.28
    o
    1.27
    Activations Density 0.000%

    No Known Activations