© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83500
    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_0_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
    ↵↵
    1.59
    고
    1.42
    다
    1.38
    ۵
    1.34
    ue
    1.30
    ﺖ
    1.29
    ot
    1.21
    시
    1.21
    in
    1.19
    ﺢ
    1.17
    POSITIVE LOGITS
    1.80
    ي
    1.53
    ק
    1.45
    ن
    1.34
     that
    1.28
    berly
    1.27
    ס
    1.21
    ys
    1.20
    n
    1.17
     a
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.