© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 732
    Prev
    Next
    INDEX
    Explanations

    `"{", "`", `"`

    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_38_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
     ن
    0.39
    лети
    0.38
    <0x87>
    0.37
     انك
    0.37
    صاف
    0.37
     Denise
    0.36
    لیسی
    0.36
     править
    0.36
    Variance
    0.35
    মেয়
    0.35
    POSITIVE LOGITS
    闢
    0.39
     clearly
    0.39
     पिया
    0.38
     gray
    0.38
     tyd
    0.37
    冧
    0.37
     mód
    0.37
     live
    0.36
    Clearly
    0.36
     Clearly
    0.36
    Activations Density 0.075%

    No Known Activations