© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41334
    Prev
    Next
    INDEX
    Explanations

    845 Sherbrooke

    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_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ঁ
    0.21
    𝙤
    0.21
    graphql
    0.21
    ildiği
    0.20
     производится
    0.20
    ків
    0.20
    क
    0.20
    рд
    0.19
    ilish
    0.19
    纜
    0.19
    POSITIVE LOGITS
     concerning
    0.24
     fighter
    0.24
     fian
    0.23
     musician
    0.23
     sporty
    0.23
     partisan
    0.22
     fluency
    0.22
     Cla
    0.21
     fighters
    0.21
     ARM
    0.21
    Activations Density 0.003%

    No Known Activations