© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162595
    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_2_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
     It
    1.77
    is
    1.67
    o
    1.55
    on
    1.52
    et
    1.51
    ra
    1.44
    '
    1.43
    hi
    1.30
    u
    1.25
    os
    1.23
    POSITIVE LOGITS
    ۵
    1.55
    이었
    1.49
    ج
    1.44
    지
    1.41
    이지만
    1.33
    ۴
    1.33
    И
    1.31
    ४
    1.30
    ع
    1.28
    К
    1.28
    Activations Density 0.000%

    No Known Activations