© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54788
    Prev
    Next
    INDEX
    Explanations

    doctor, physician, year, propagation

    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_30_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
    いえ
    0.36
    கு
    0.34
    Ⲕ
    0.34
    prefixes
    0.31
    Lähteet
    0.30
    ยุ
    0.30
    jeh
    0.30
    '][$
    0.30
    又能
    0.30
    了吗
    0.29
    POSITIVE LOGITS
     During
    0.35
    魈
    0.35
    께서
    0.35
    During
    0.34
     Chol
    0.34
     করছিলাম
    0.34
     egyik
    0.33
     വലിയ
    0.33
    来到了
    0.33
     শিবিরে
    0.33
    Activations Density 0.042%

    No Known Activations