© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45963
    Prev
    Next
    INDEX
    Explanations

    numbers and slashes

    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_10_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
    Weekly
    0.73
    Guid
    0.73
    Cec
    0.70
    Globalization
    0.70
    Gui
    0.68
    Integrated
    0.68
    6
    0.68
    El
    0.67
    Gu
    0.67
    Instrument
    0.67
    POSITIVE LOGITS
     és
    0.64
     OpenCV
    0.60
     poderá
    0.59
     SEO
    0.58
     și
    0.58
     '
    0.57
     NDA
    0.57
     fale
    0.57
    issimo
    0.56
    និង
    0.55
    Activations Density 0.000%

    No Known Activations