© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215725
    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_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ر
    1.70
    at
    1.55
    on
    1.36
    ب
    1.35
    ه
    1.31
    ు
    1.30
    he
    1.26
    ar
    1.24
    مي
    1.22
    en
    1.20
    POSITIVE LOGITS
    ם
    1.27
     to
    1.16
     که
    1.06
     C
    1.05
     &
    1.04
    (
    1.03
    که
    0.99
    ۹
    0.99
     yang
    0.97
     you
    0.96
    Activations Density 0.000%

    No Known Activations