© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194891
    Prev
    Next
    INDEX
    Explanations

    vision or class

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    物
    0.75
    物的
    0.69
    物の
    0.65
     vật
    0.62
     物
    0.55
    物を
    0.55
    物は
    0.54
    物に
    0.52
    물
    0.51
    물의
    0.48
    POSITIVE LOGITS
    類
    0.46
    nu
    0.43
    類的
    0.42
    类
    0.42
     nu
    0.41
     класса
    0.40
     class
    0.40
     Class
    0.40
    сква
    0.39
    ぬ
    0.39
    Activations Density 0.010%

    No Known Activations