© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212701
    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_19_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
    ל
    0.54
    №
    0.52
    ي
    0.50
    ח
    0.50
    억원
    0.50
    ներ
    0.49
    ཌ
    0.48
    ק
    0.47
    urile
    0.47
    сок
    0.47
    POSITIVE LOGITS
     Conn
    0.53
     circum
    0.49
     repaired
    0.49
     roommate
    0.48
     аутохтони
    0.47
     アップ
    0.47
     完全
    0.47
     speech
    0.46
     Garcia
    0.46
     McCarthy
    0.46
    Activations Density 0.000%

    No Known Activations