© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8502
    Prev
    Next
    INDEX
    Explanations

    operators symbols

    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_13_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
     م
    0.55
     m
    0.54
     day
    0.53
     program
    0.49
    >
    0.49
     animal
    0.49
     u
    0.49
     software
    0.48
     platform
    0.48
     manual
    0.47
    POSITIVE LOGITS
     uczniów
    0.57
    śmy
    0.53
    ců
    0.53
    𝕖
    0.52
    cated
    0.52
    ḓ
    0.52
    <unused678>
    0.51
     размещения
    0.51
     SalesLT
    0.50
     vacanam
    0.50
    Activations Density 0.000%

    No Known Activations