© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32918
    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
    給
    0.37
    给
    0.34
    зион
    0.33
    缓
    0.33
     Giving
    0.33
     給
    0.33
     level
    0.32
     give
    0.32
    Giving
    0.32
     giving
    0.31
    POSITIVE LOGITS
    quellen
    0.33
     SOURCES
    0.32
     مبت
    0.30
    เดียวกัน
    0.29
     источников
    0.29
    สัญญาณ
    0.29
    任命
    0.29
    ጆ
    0.29
    ᡤ
    0.29
    যেন
    0.29
    Activations Density 0.000%

    No Known Activations