© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179876
    Prev
    Next
    INDEX
    Explanations

    historical texts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Gy
    0.48
     Gy
    0.47
     gy
    0.43
     Gyr
    0.43
    GY
    0.42
     GY
    0.42
     gyr
    0.41
    亰
    0.40
    Man
    0.39
    greedy
    0.39
    POSITIVE LOGITS
     аб
    0.40
     Dtsch
    0.39
    첨
    0.37
    nich
    0.36
    coder
    0.36
     lê
    0.36
     vulve
    0.36
     مر
    0.35
    CodeGen
    0.35
    颛
    0.34
    Activations Density 0.000%

    No Known Activations