© 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. 40788
    Prev
    Next
    INDEX
    Explanations

    digestive system

    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
    מ
    0.85
    ו
    0.75
    منا
    0.75
    ।
    0.72
    ח
    0.66
     that
    0.66
     moistur
    0.66
    ।,
    0.64
     in
    0.64
     synthase
    0.63
    POSITIVE LOGITS
    اري
    0.78
     Andere
    0.77
    ير
    0.71
     consiguió
    0.70
    Cancelar
    0.67
    _
    0.66
    تهم
    0.66
     Pré
    0.64
    어졌
    0.63
    <0xA2>
    0.63
    Activations Density 0.001%

    No Known Activations