© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200252
    Prev
    Next
    INDEX
    Explanations

    listing items or options

    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_37_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
     salário
    0.61
     salario
    0.55
     payment
    0.54
     salary
    0.53
     зар
    0.52
    薪
    0.52
     salaries
    0.51
     वेतन
    0.50
     सैलरी
    0.49
    salary
    0.47
    POSITIVE LOGITS
    idxs
    0.39
     Indexes
    0.39
     عمليات
    0.38
     বসবাসের
    0.38
    ⟧
    0.37
    indexes
    0.36
     تخلی
    0.36
    bangan
    0.36
    Literal
    0.36
    展开
    0.36
    Activations Density 0.008%

    No Known Activations