© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78383
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    STTS
    0.59
    }";
    0.59
     العزيز
    0.57
     tí
    0.56
    ти
    0.55
     addirittura
    0.55
    an
    0.53
    ុត
    0.53
    u
    0.53
    েও
    0.52
    POSITIVE LOGITS
    _
    0.63
    ও
    0.63
    क्स
    0.57
    도
    0.56
    した
    0.55
    পে
    0.55
    恝
    0.54
    दत
    0.53
    된
    0.53
    د
    0.52
    Activations Density 0.000%

    No Known Activations