© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85375
    Prev
    Next
    INDEX
    Explanations

    fish oil supplement

    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_3_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
    ص
    0.69
    σ
    0.64
    al
    0.63
    at
    0.61
    پ
    0.59
    person
    0.58
    лыгы
    0.58
    gings
    0.57
    cı
    0.56
    श्रे
    0.55
    POSITIVE LOGITS
    メートル
    0.61
    _
    0.61
     botones
    0.59
     isn
    0.56
     októ
    0.56
     バ
    0.56
     aspires
    0.55
     didn
    0.55
     deset
    0.54
    DesIP
    0.53
    Activations Density 0.002%

    No Known Activations