© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205516
    Prev
    Next
    INDEX
    Explanations

    devoted to

    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_10_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
    to
    1.30
    th
    0.82
    city
    0.82
    new
    0.82
    1
    0.81
    中
    0.78
    fte
    0.77
    tier
    0.76
    6
    0.76
    ۳
    0.75
    POSITIVE LOGITS
    0.99
     bikes
    0.72
     insomnia
    0.70
     HTTPS
    0.70
    ’
    0.68
     mahi
    0.68
     `:`,
    0.68
     kayaks
    0.67
     attrakt
    0.67
     oxi
    0.67
    Activations Density 0.001%

    No Known Activations