© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208976
    Prev
    Next
    INDEX
    Explanations

    factorial and loop variable i

    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_20_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
     rew
    0.46
     reversal
    0.44
     অভিহিত
    0.44
    คนที่
    0.44
    够
    0.44
     tradeoff
    0.42
     তথ
    0.42
    และการ
    0.42
     rework
    0.42
    ობას
    0.41
    POSITIVE LOGITS
    hwar
    0.47
    व्यक्तित्व
    0.46
     फ्लावर
    0.46
     Decorative
    0.45
    恹
    0.45
    𝗙
    0.44
     cerámica
    0.44
    ıcı
    0.43
    ARS
    0.43
     кеңсесинде
    0.42
    Activations Density 0.000%

    No Known Activations