© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197284
    Prev
    Next
    INDEX
    Explanations

    database migrations

    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_26_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
    are
    0.47
    rophication
    0.43
    बम
    0.42
    asing
    0.41
    arg
    0.41
    讥
    0.40
    uding
    0.39
     जगत
    0.39
    icago
    0.39
    rierung
    0.39
    POSITIVE LOGITS
    같이
    0.45
     gibi
    0.44
     ข้อ
    0.43
     MIM
    0.43
     aşağı
    0.41
    比如
    0.41
    ﱢ
    0.41
    например
    0.40
    เช่น
    0.40
     parfois
    0.40
    Activations Density 0.000%

    No Known Activations