© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16179
    Prev
    Next
    INDEX
    Explanations

    contribution and trends

    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_40_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
     ร้อย
    0.38
     emotion
    0.36
    logo
    0.36
    emotion
    0.36
    Website
    0.36
    денти
    0.36
    YouTube
    0.36
    राष्ट
    0.35
    Galaxy
    0.35
     }^{[
    0.35
    POSITIVE LOGITS
     Contribution
    0.48
     contribution
    0.47
     trends
    0.46
    Contribution
    0.45
     Trends
    0.44
     বিতর্ক
    0.44
    Trends
    0.43
     trend
    0.42
     ট্রেন
    0.40
     TREND
    0.40
    Activations Density 0.202%

    No Known Activations