© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74493
    Prev
    Next
    INDEX
    Explanations

    GCSE mathematics or biology

    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_31_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
     Brit
    0.38
    Msg
    0.38
    oprol
    0.38
     brin
    0.38
     Node
    0.37
     FAO
    0.37
     EU
    0.37
     Euro
    0.37
    訥
    0.36
     Brandenburg
    0.36
    POSITIVE LOGITS
    FQ
    0.37
    错误的
    0.36
    鞆
    0.36
     интерпре
    0.36
    解决
    0.35
    指导
    0.35
    ர்க்க
    0.35
     interpretive
    0.35
    DR
    0.34
     해석
    0.34
    Activations Density 0.001%

    No Known Activations