© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 19035
    Prev
    Next
    INDEX
    Explanations

    decimal places

    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_34_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
     repetitive
    0.38
     dap
    0.37
    日子
    0.37
     зах
    0.36
     নদীতে
    0.36
    udit
    0.36
     punishment
    0.36
    ழுத
    0.35
    ✗
    0.35
     Cyclic
    0.35
    POSITIVE LOGITS
     centimeter
    0.57
     microseconds
    0.56
     millimeter
    0.55
     minute
    0.53
     centimeters
    0.52
     millimeters
    0.52
     milli
    0.49
     milliseconds
    0.49
     mill
    0.48
     cents
    0.48
    Activations Density 0.007%

    No Known Activations