© 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. 212797
    Prev
    Next
    INDEX
    Explanations

    sex

    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
     нанесе
    0.49
    Mono
    0.48
     Mono
    0.46
    Pierre
    0.45
    Rio
    0.44
     Rio
    0.42
    祁
    0.38
     Pierre
    0.38
     mono
    0.38
    이고
    0.38
    POSITIVE LOGITS
     Великобрита
    0.40
    Ỹ
    0.37
     yaml
    0.36
     bomb
    0.36
     Marley
    0.36
    ADH
    0.36
     Marcy
    0.36
    мережа
    0.35
     interprets
    0.35
     Али
    0.35
    Activations Density 0.000%

    No Known Activations