© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33235
    Prev
    Next
    INDEX
    Explanations

    Korean words and greetings

    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_31_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
     respald
    0.38
     земли
    0.36
    zano
    0.36
    OfWeek
    0.36
    '/
    0.36
    綱
    0.36
     asum
    0.35
    スキル
    0.35
     الرئيسية
    0.34
     て
    0.34
    POSITIVE LOGITS
     Universe
    0.43
     troubled
    0.39
     Tamp
    0.36
     μπ
    0.36
     Flex
    0.36
    iguation
    0.36
     Pyongyang
    0.36
     Konstant
    0.35
    binder
    0.35
    addWidget
    0.35
    Activations Density 0.003%

    No Known Activations