© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45105
    Prev
    Next
    INDEX
    Explanations

    UNITED

    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_10_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
    '
    0.57
     an
    0.54
     };
    0.50
     Christine
    0.50
     lam
    0.48
    ’
    0.48
    传
    0.48
    ان
    0.48
    '};
    0.48
     SIST
    0.48
    POSITIVE LOGITS
    rencies
    0.52
    landmark
    0.50
    root
    0.50
    soil
    0.50
    land
    0.49
    OV
    0.48
     القاهرة
    0.48
     পড়ছে
    0.48
    regulatory
    0.48
    fficacy
    0.48
    Activations Density 0.000%

    No Known Activations