© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 120992
    Prev
    Next
    INDEX
    Explanations

    monochrome, grayscale, OLED, plastic

    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_37_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
    電流
    0.44
    Convention
    0.42
     Antip
    0.41
    背景
    0.40
    エンド
    0.37
    MoodAnalyser
    0.37
    否
    0.36
    ホワイト
    0.36
    Conservation
    0.36
    ılım
    0.36
    POSITIVE LOGITS
     irreducible
    0.40
    করে
    0.39
     incurable
    0.39
     replaceable
    0.39
     reducible
    0.38
     permanent
    0.38
     acrylic
    0.38
     degree
    0.37
     fator
    0.37
    芮
    0.37
    Activations Density 0.000%

    No Known Activations