© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193983
    Prev
    Next
    INDEX
    Explanations

    PWM duty cycle

    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_15_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
     zone
    0.55
     brakes
    0.50
    速度
    0.48
    stairs
    0.48
    体
    0.46
     frase
    0.46
     voltage
    0.45
    Within
    0.45
     driving
    0.45
    网络
    0.45
    POSITIVE LOGITS
     pecuniary
    0.64
    瑉
    0.64
     deceduto
    0.61
    ']+
    0.60
    getAbsolutePath
    0.57
    GALAD
    0.56
     defects
    0.56
     DISPLAYSURF
    0.56
     Gandhiji
    0.56
     Johansson
    0.55
    Activations Density 0.002%

    No Known Activations