© 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. 162686
    Prev
    Next
    INDEX
    Explanations

    soybeans

    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
     in
    1.28
     incentivize
    1.02
     yanı
    1.02
    ib
    0.97
    ק
    0.96
     добав
    0.95
    િ
    0.95
     actinides
    0.95
     confirm
    0.93
    ાદ
    0.92
    POSITIVE LOGITS
    is
    1.63
    an
    1.54
    n
    1.40
    ان
    1.34
    하는
    1.29
    리
    1.28
    لي
    1.23
    습니다
    1.22
    speople
    1.22
    н
    1.20
    Activations Density 0.000%

    No Known Activations