© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40270
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    㷫
    0.37
    вь
    0.36
    主張
    0.35
    خش
    0.34
    arsk
    0.34
     Kes
    0.33
     footwear
    0.33
    ذه
    0.33
    ismet
    0.33
    ара
    0.33
    POSITIVE LOGITS
    explique
    0.43
     کرتے
    0.43
     partie
    0.39
     ஏ
    0.37
    como
    0.37
    ማ
    0.37
    юр
    0.36
    abal
    0.35
    िये
    0.35
    repl
    0.35
    Activations Density 0.002%

    No Known Activations