© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52758
    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_31_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
    抻
    0.39
    ভাবে
    0.38
     सिंपली
    0.38
     plotly
    0.37
     Unemployment
    0.37
     গ্রাহ
    0.36
    ଼
    0.35
    gangen
    0.35
     пля
    0.35
    醤
    0.35
    POSITIVE LOGITS
     atro
    0.43
    仪式
    0.39
     cuid
    0.38
     लिखना
    0.36
     Surya
    0.36
     цере
    0.36
     ceremonia
    0.35
     Siro
    0.35
    rmse
    0.35
     damn
    0.35
    Activations Density 0.000%

    No Known Activations