© 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. 36892
    Prev
    Next
    INDEX
    Explanations

    start of a statement identifier

    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
    phys
    0.40
    supervised
    0.39
    phine
    0.38
    VEL
    0.38
    lectric
    0.38
    FRS
    0.38
    STONE
    0.38
     physiques
    0.38
    lichen
    0.37
    _______
    0.37
    POSITIVE LOGITS
    urie
    0.42
    および
    0.36
     কর্তৃক
    0.35
     Sj
    0.35
     विवा
    0.35
     Haga
    0.34
     दंड
    0.33
     центром
    0.33
     চালিয়ে
    0.33
     sugary
    0.33
    Activations Density 0.000%

    No Known Activations