© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19748
    Prev
    Next
    INDEX
    Explanations

    "adult supervision"

    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_15_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
    字段
    0.45
     isothermal
    0.44
    rosophila
    0.44
     ";"
    0.43
    我們的
    0.40
     чувства
    0.40
     tenéis
    0.39
     samoglas
    0.39
    
    0.39
    隘
    0.39
    POSITIVE LOGITS
     другой
    0.46
     விஜ
    0.44
    τζ
    0.44
     vyp
    0.43
     Aden
    0.43
    ₀
    0.42
     Young
    0.42
    letal
    0.42
     Zero
    0.41
     উদ্দিন
    0.41
    Activations Density 0.034%

    No Known Activations