© 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. 62467
    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_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
     IPM
    0.52
     ufficiale
    0.50
    береж
    0.50
     chmod
    0.50
    Ḫ
    0.50
    проце
    0.50
     riz
    0.49
     Djibouti
    0.49
    ચારી
    0.48
     perdagangan
    0.48
    POSITIVE LOGITS
    many
    0.57
    {
    0.54
    vis
    0.52
    as
    0.51
    may
    0.50
    ota
    0.50
    will
    0.50
    any
    0.50
    (
    0.50
    velocity
    0.48
    Activations Density 0.000%

    No Known Activations