© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102854
    Prev
    Next
    INDEX
    Explanations

    Heydar Aliyev

    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_1_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
    ла
    1.34
    는
    1.26
    al
    1.12
    것
    1.07
    是
    1.06
    ა
    0.95
    ט
    0.95
    は
    0.93
    เป็น
    0.93
    ಾ
    0.90
    POSITIVE LOGITS
    t
    1.54
    ר
    1.26
    in
    1.15
    rms
    1.14
    ars
    1.09
    1
    1.08
    f
    1.04
    tut
    1.03
    tint
    1.00
    >
    0.99
    Activations Density 0.000%

    No Known Activations