© 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. 25407
    Prev
    Next
    INDEX
    Explanations

    galaxies, faint, red dwarf stars

    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
    <0x0D>
    0.31
    rup
    0.26
    वणी
    0.25
    ু
    0.25
    m
    0.25
    /
    0.25
    ie
    0.24
     veloce
    0.24
     Affairs
    0.24
     mitochondria
    0.24
    POSITIVE LOGITS
     астро
    0.32
     galaxies
    0.32
     astronomers
    0.29
    သည်
    0.27
    Мар
    0.27
    Прави
    0.27
    憸
    0.26
     preguntas
    0.26
    Нор
    0.26
    Он
    0.26
    Activations Density 0.038%

    No Known Activations