© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40992
    Prev
    Next
    INDEX
    Explanations

    should followed by 'be', 'occur', 'include', 'provide'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    K
    0.31
    O
    0.31
    Sports
    0.25
    Tum
    0.25
    ول
    0.24
    Pager
    0.24
    Literature
    0.24
    Tracker
    0.23
    पक
    0.23
     Cartoon
    0.23
    POSITIVE LOGITS
    약을
    0.27
     التي
    0.26
    và
    0.26
    \}$,
    0.25
    have
    0.25
     أيضا
    0.25
     რომელიც
    0.24
    소가
    0.24
     کاهش
    0.23
    ameva
    0.23
    Activations Density 0.031%

    No Known Activations