© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39831
    Prev
    Next
    INDEX
    Explanations

    noise cancelling headphones

    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_3_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
    i
    0.86
    0.86
    o
    0.85
    '
    0.79
     summar
    0.69
    ate
    0.67
     secretions
    0.66
     reasoned
    0.66
     annotation
    0.65
    u
    0.64
    POSITIVE LOGITS
    ك
    1.11
    ى
    0.88
    م
    0.83
    り
    0.80
    し
    0.79
    يا
    0.78
    حي
    0.78
    ю
    0.76
    الي
    0.74
    ف
    0.72
    Activations Density 0.027%

    No Known Activations