© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118078
    Prev
    Next
    INDEX
    Explanations

    Japanese, Korean, and Chinese grammatical elements

    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_27_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
     вас
    0.45
     treball
    0.45
     поколения
    0.43
    𝘣
    0.43
     ваш
    0.43
     सूरज
    0.43
     எண்ணிக்க
    0.42
     sebagainya
    0.42
     ملا
    0.42
     Lebih
    0.42
    POSITIVE LOGITS
    水
    0.39
     compression
    0.37
    ฐ
    0.36
     나의
    0.36
    갈
    0.35
    铺
    0.35
    LevelLinking
    0.35
     courting
    0.35
     푸
    0.35
    压缩
    0.34
    Activations Density 0.001%

    No Known Activations