© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31499
    Prev
    Next
    INDEX
    Explanations

    special characters

    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_50_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
    ❏
    0.37
     longue
    0.37
    ␶
    0.36
     Facial
    0.36
    facial
    0.35
     coexist
    0.35
     Holiday
    0.34
     ফোনের
    0.34
    (;
    0.34
    
    0.33
    POSITIVE LOGITS
    ?-
    1.00
     &-
    0.90
     ?-
    0.86
    "-
    0.81
    *-
    0.77
    '-
    0.76
     *-
    0.73
    #-
    0.73
     #-
    0.73
    ."-
    0.71
    Activations Density 1.374%

    No Known Activations