© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61283
    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_2_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
    ע
    1.35
    מ
    1.13
    ن
    1.10
    an
    1.06
    ה
    1.02
    א
    1.02
    เป็น
    0.95
    י
    0.95
    נ
    0.95
    c
    0.91
    POSITIVE LOGITS
     roue
    0.84
    시
    0.75
     grote
    0.74
     cinque
    0.73
     فيلم
    0.73
     miljoen
    0.73
     श्रद्धालुओं
    0.73
     botella
    0.71
     fortr
    0.71
     piattaforma
    0.71
    Activations Density 0.000%

    No Known Activations