© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 103395
    Prev
    Next
    INDEX
    Explanations

    Deng Xiaoping, Chinese Characteristics

    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_16_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
    itsch
    0.58
    т
    0.55
    b
    0.51
    k
    0.50
    ع
    0.50
     Autor
    0.50
    ich
    0.49
     Mayor
    0.49
    خ
    0.46
    mayor
    0.46
    POSITIVE LOGITS
     окон
    0.64
    𒅖
    0.60
     atheros
    0.59
    ліся
    0.59
     заканчи
    0.58
     dine
    0.57
     хими
    0.57
     backseat
    0.57
     absorbs
    0.57
     техника
    0.57
    Activations Density 0.000%

    No Known Activations