© 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. 19171
    Prev
    Next
    INDEX
    Explanations

    riddles

    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
    げる
    0.44
    uet
    0.43
    utia
    0.40
    /$
    0.40
     Million
    0.39
    UREMENT
    0.38
    ITTLE
    0.38
    utional
    0.38
    uant
    0.38
     now
    0.37
    POSITIVE LOGITS
    unchecked
    0.44
     சும
    0.40
    海の
    0.39
     mous
    0.38
    Воз
    0.38
    勋
    0.38
    циям
    0.37
     Sten
    0.37
     взгля
    0.36
     strCmd
    0.36
    Activations Density 0.002%

    No Known Activations