© 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. 200088
    Prev
    Next
    INDEX
    Explanations

    sustainability

    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
     तथा
    0.39
    getpath
    0.37
    міна
    0.37
    带动
    0.37
    mixin
    0.37
    ᱾
    0.37
    état
    0.36
    状態で
    0.36
    جهزة
    0.36
     செய்து
    0.35
    POSITIVE LOGITS
    ad
    0.37
    сле
    0.37
    :
    0.36
     elite
    0.35
     escolher
    0.35
     curioso
    0.33
     ще
    0.33
     eventi
    0.33
     ý
    0.32
     COS
    0.32
    Activations Density 0.003%

    No Known Activations