© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176677
    Prev
    Next
    INDEX
    Explanations

    RED Pyro vs BLU Spy

    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_20_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
    Norton
    0.46
     Galbraith
    0.45
     Gori
    0.44
     ہوگا
    0.44
     Guel
    0.44
    ઁ
    0.43
     Lutz
    0.43
     Cang
    0.42
     fibroblasts
    0.42
    𝑁
    0.42
    POSITIVE LOGITS
    상을
    0.42
    فل
    0.41
    પણે
    0.40
    강
    0.40
    混乱
    0.39
    imp
    0.38
    대학
    0.38
    agm
    0.38
    飛行
    0.38
    合
    0.38
    Activations Density 0.002%

    No Known Activations