© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46341
    Prev
    Next
    INDEX
    Explanations

    car mileage and distance

    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_22_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
    යෙන්
    0.46
     femelle
    0.41
     distribusi
    0.41
     அனுப்ப
    0.40
    蒸汽
    0.40
     вечером
    0.38
    तमंद
    0.38
    ܡ
    0.38
     खबरों
    0.37
     जानकार
    0.37
    POSITIVE LOGITS
    ່ຽ
    0.48
    擂
    0.44
    Evaluate
    0.40
    nex
    0.39
    حل
    0.39
     Analysis
    0.38
     Hein
    0.38
    عا
    0.37
     ран
    0.37
     решение
    0.37
    Activations Density 0.001%

    No Known Activations