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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6251
    Prev
    Next
    INDEX
    Explanations

    allows or enables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    可能會
    0.44
    輯
    0.42
     pourrait
    0.39
     ನಿಜ
    0.39
     そう
    0.37
    有可能
    0.37
    |<\
    0.36
    麻煩
    0.36
    ^{*}(
    0.35
     الناتج
    0.35
    POSITIVE LOGITS
     ensures
    1.13
     allows
    1.11
     prevents
    1.08
     enables
    1.07
     позволяет
    1.02
    Allows
    1.01
     обеспечивает
    0.98
     eliminates
    0.96
     Allows
    0.95
    allows
    0.95
    Activations Density 0.587%

    No Known Activations