© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26756
    Prev
    Next
    INDEX
    Explanations

    `Grade` or `special needs`

    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_40_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
     kn
    0.45
     italien
    0.42
     italian
    0.42
    ద్దా
    0.42
     kou
    0.41
     shaw
    0.39
    Shaw
    0.38
     kih
    0.38
    川
    0.38
     italy
    0.37
    POSITIVE LOGITS
    Loc
    0.38
     Loc
    0.38
    वण
    0.38
     Asha
    0.35
     草
    0.35
     Bilingual
    0.34
     язы
    0.34
     Drop
    0.34
     OSI
    0.34
    drop
    0.33
    Activations Density 0.016%

    No Known Activations