© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1064
    Prev
    Next
    INDEX
    Explanations

    https:// links

    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_39_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
    neuron
    0.35
    ਹੁ
    0.34
    farbe
    0.33
    বনে
    0.33
    ியே
    0.32
    成分
    0.31
    ι
    0.31
    状況
    0.30
    uales
    0.30
    Barn
    0.30
    POSITIVE LOGITS
     русской
    0.36
    पदी
    0.35
    ucers
    0.34
     Fancy
    0.34
     골
    0.34
    equival
    0.34
     equival
    0.34
     chips
    0.33
     موس
    0.33
     ಹಣ
    0.33
    Activations Density 0.061%

    No Known Activations