© 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. 91889
    Prev
    Next
    INDEX
    Explanations

    Google Search Console, Relevance, Range

    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
     در
    0.77
    ا
    0.73
    ت
    0.69
    ación
    0.66
    de
    0.64
    在
    0.64
    ри
    0.63
    ى
    0.61
    การ
    0.59
    но
    0.59
    POSITIVE LOGITS
    CAT
    0.55
    ේ
    0.55
    end
    0.54
     as
    0.53
    AW
    0.53
    ANU
    0.53
    DZ
    0.51
    order
    0.49
    house
    0.48
    BITS
    0.48
    Activations Density 0.002%

    No Known Activations