© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85184
    Prev
    Next
    INDEX
    Explanations

    yellow exclamation marks

    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_18_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
     Reglamento
    0.25
     errors
    0.25
     ۵
    0.23
    imenta
    0.23
    マガ
    0.23
     Bick
    0.22
     Ս
    0.22
     OpenAPI
    0.22
     创建
    0.22
     HTML
    0.21
    POSITIVE LOGITS
     gardener
    0.26
    шил
    0.23
    lső
    0.22
    вшихся
    0.22
     wygod
    0.22
     maintains
    0.22
    lide
    0.22
    ربه
    0.22
    療
    0.21
    ለት
    0.21
    Activations Density 0.000%

    No Known Activations