© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54974
    Prev
    Next
    INDEX
    Explanations

    numbers and times

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    Howard
    0.43
     Howard
    0.37
    ྵ
    0.35
    rales
    0.35
    Kol
    0.34
    шты
    0.34
     Kol
    0.34
    REGISTER
    0.33
    ził
    0.33
    鎿
    0.32
    POSITIVE LOGITS
     terminology
    0.39
     clinic
    0.38
     stylish
    0.38
     Clinic
    0.38
    우스
    0.38
     Islamic
    0.37
     droughts
    0.36
     glamorous
    0.36
     nomenclature
    0.36
    Btn
    0.35
    Activations Density 0.014%

    No Known Activations