© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15127
    Prev
    Next
    INDEX
    Explanations

    systolic blood pressure

    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_13_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
     पदार्थों
    0.20
    
    0.18
    కా
    0.18
    ごはん
    0.17
     jueces
    0.17
    ค
    0.17
    في
    0.17
     ایپل
    0.17
    చ
    0.16
    เค
    0.16
    POSITIVE LOGITS
    s
    0.21
    ów
    0.17
     volgens
    0.17
    ous
    0.16
    .
    0.16
    ất
    0.16
     inscreva
    0.16
     code
    0.16
     benchmarking
    0.16
     benchmark
    0.15
    Activations Density 0.004%

    No Known Activations