© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235549
    Prev
    Next
    INDEX
    Explanations

    Cubism, Cubist, Cézanne, shapes, simultaneity

    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_32_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
    ﺟ
    0.43
    基地
    0.41
    Dens
    0.38
     décider
    0.37
    ฐาน
    0.36
     décidé
    0.36
    決定
    0.36
    ুজ
    0.36
    тити
    0.36
    Cm
    0.35
    POSITIVE LOGITS
     punctatis
    0.41
     화면
    0.41
     Lat
    0.40
    ெழு
    0.39
     weathered
    0.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
     ഇരു
    0.38
     Vec
    0.38
     Chia
    0.38
     BEAUT
    0.38
    Activations Density 0.002%

    No Known Activations