© 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. 193876
    Prev
    Next
    INDEX
    Explanations

    fonts and related assets

    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
    Negative Logits
     दशा
    0.50
     тестирование
    0.50
     туда
    0.49
     IllegalArgument
    0.49
    OpportunitiesBy
    0.49
     localVarAccept
    0.48
    vet
    0.48
     `=`
    0.48
    textAllCaps
    0.47
    himanyu
    0.47
    POSITIVE LOGITS
     kerak
    0.55
     cac
    0.52
    ・・・
    0.49
    如果
    0.48
    okość
    0.48
    我的
    0.47
     twelve
    0.47
    <0xA5>
    0.46
     teilweise
    0.46
    ار
    0.44
    Activations Density 0.001%

    No Known Activations