© 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. 84692
    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
     of
    1.31
     to
    1.30
     on
    1.28
    ियों
    1.26
     with
    1.23
    م
    1.14
    ن
    1.05
     from
    1.02
    ून
    1.01
    ม
    1.01
    POSITIVE LOGITS
    u
    1.39
    i
    1.02
    and
    1.00
    x
    1.00
    一定的
    0.88
    in
    0.82
    ו
    0.82
     agricole
    0.81
    /
    0.80
    planting
    0.79
    Activations Density 0.000%

    No Known Activations