© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143788
    Prev
    Next
    INDEX
    Explanations

    time related concepts

    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_46_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
     leap
    1.48
     Leap
    1.32
    leap
    1.23
     Sundays
    0.94
     Saturdays
    0.94
     leaps
    0.93
     leaped
    0.93
     holidays
    0.91
    闰
    0.91
     Holidays
    0.89
    POSITIVE LOGITS
    Catagory
    0.41
    lineTo
    0.40
    órico
    0.34
     스트
    0.34
     Witch
    0.34
    mss
    0.34
    പ്പിച്ചി
    0.33
     Poc
    0.32
     insulation
    0.32
    ะไร
    0.32
    Activations Density 0.060%

    No Known Activations