© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200352
    Prev
    Next
    INDEX
    Explanations

    เก่ง, เพราะ, เก๋, เพลิด

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सावधान
    0.40
    หาร
    0.38
    ytuc
    0.38
    畊
    0.38
    HSV
    0.37
     своих
    0.37
     trouver
    0.36
    തര
    0.36
    ྗ
    0.35
    NFL
    0.35
    POSITIVE LOGITS
     Instrumental
    0.38
     डॉक्यूमेंट्री
    0.38
     instrumental
    0.37
     endowment
    0.34
    vič
    0.34
     fred
    0.33
    [,-
    0.33
     rumoured
    0.33
    ോ
    0.33
     incoherent
    0.33
    Activations Density 0.000%

    No Known Activations