© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44006
    Prev
    Next
    INDEX
    Explanations

    `#` and `%` placeholders

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    0.56
     mundo
    0.54
    ИК
    0.53
    ناف
    0.52
     으로
    0.50
    فی
    0.50
    НА
    0.50
    Когда
    0.50
     работой
    0.50
    یس
    0.49
    POSITIVE LOGITS
     Mitarbeiter
    0.49
     Rent
    0.49
    le
    0.48
    級
    0.47
    ppery
    0.47
    étais
    0.46
    eta
    0.46
     Payroll
    0.46
     Layton
    0.46
     Perks
    0.46
    Activations Density 0.000%

    No Known Activations