© 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. 46401
    Prev
    Next
    INDEX
    Explanations

    golang grpc server, telegram bot, redis

    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
    Negative Logits
    rana
    0.45
     យើង
    0.44
    𝙋
    0.43
     você
    0.42
    posti
    0.41
     Лі
    0.40
     우리가
    0.40
     我們
    0.40
    thing
    0.40
     Gop
    0.40
    POSITIVE LOGITS
     impec
    0.43
     conglomer
    0.42
     incluso
    0.40
    间
    0.40
     direttamente
    0.39
     específicamente
    0.39
     capable
    0.39
     acon
    0.38
     intersections
    0.38
     individually
    0.38
    Activations Density 0.000%

    No Known Activations