© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63979
    Prev
    Next
    INDEX
    Explanations

    Master Boot Record

    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_41_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
     цен
    0.45
    மூ
    0.40
    DNA
    0.39
     Eureka
    0.39
     DNA
    0.38
    স্তা
    0.38
     Husky
    0.38
    徹
    0.38
     Cliff
    0.38
     Jol
    0.37
    POSITIVE LOGITS
     블랙
    0.56
     black
    0.55
    ブラック
    0.55
     blacks
    0.54
     чор
    0.52
     accretion
    0.52
     سیاه
    0.52
     super
    0.50
     Black
    0.49
    黑
    0.48
    Activations Density 0.003%

    No Known Activations