© 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. 9557
    Prev
    Next
    INDEX
    Explanations

    predicting next word in sequence

    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
    방
    0.38
     draw
    0.38
    쩔
    0.37
     imputation
    0.37
    ক্ষে
    0.37
     drawings
    0.37
    كب
    0.36
     DRAW
    0.35
    顺
    0.35
     Santé
    0.35
    POSITIVE LOGITS
    系列
    0.52
     After
    0.49
     после
    0.48
     серии
    0.46
     selepas
    0.44
     prije
    0.44
     Después
    0.43
     after
    0.43
     بعد
    0.43
     серия
    0.43
    Activations Density 0.048%

    No Known Activations