© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69465
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Bridges
    0.42
    ayashi
    0.40
     العشر
    0.39
    樘
    0.39
     Det
    0.37
    Qs
    0.37
    𝚈
    0.36
    㜿
    0.36
    ാനം
    0.36
     Ten
    0.35
    POSITIVE LOGITS
     christ
    1.31
    christ
    1.27
    Christ
    1.20
     Christ
    1.11
     Christen
    1.00
    CHRIST
    0.95
     CHRIST
    0.91
     Christie
    0.72
    基督
    0.72
     Christi
    0.71
    Activations Density 0.027%

    No Known Activations