© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209441
    Prev
    Next
    INDEX
    Explanations

    consulta SQL

    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_5_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
    は
    1.52
    ید
    1.45
    کو
    1.45
     کل
    1.43
    یت
    1.40
    وی
    1.38
    ای
    1.37
    کار
    1.36
    ди
    1.35
     ذکر
    1.34
    POSITIVE LOGITS
    .
    1.27
    1.15
    ell
    0.98
     erleben
    0.98
     zerstört
    0.98
     teilen
    0.96
    et
    0.93
    鉆
    0.91
    ojen
    0.89
    ober
    0.86
    Activations Density 0.002%

    No Known Activations