© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229460
    Prev
    Next
    INDEX
    Explanations

    Chinese Pinyin and word endings

    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_6_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
     in
    1.09
     في
    1.06
    '
    1.06
    Sh
    0.93
    Rate
    0.92
     σε
    0.89
    Link
    0.86
    Beam
    0.86
     an
    0.82
    Scal
    0.80
    POSITIVE LOGITS
    기
    1.51
    та
    1.35
    ח
    1.35
    یس
    1.34
    나
    1.34
    د
    1.28
    ش
    1.23
    ש
    1.23
    스
    1.21
    다
    1.19
    Activations Density 0.002%

    No Known Activations