© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88870
    Prev
    Next
    INDEX
    Explanations

    serves customers or you

    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_11_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
    en
    0.63
     world
    0.61
     restaurant
    0.57
     #
    0.56
    खाना
    0.54
    ለም
    0.54
     $
    0.53
    ia
    0.52
     Sokol
    0.52
     _
    0.51
    POSITIVE LOGITS
    ið
    0.56
     सीएचसी
    0.53
     castes
    0.52
     नक्सलियों
    0.52
    σει
    0.52
    ਸੀ
    0.52
     uttered
    0.51
    ando
    0.51
    щений
    0.51
    æ
    0.50
    Activations Density 0.001%

    No Known Activations