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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37559
    Prev
    Next
    INDEX
    Explanations

    formatting separators

    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_11_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
    at
    0.64
    Substitute
    0.60
    Sally
    0.59
    pe
    0.57
    ți
    0.57
    ț
    0.57
    ط
    0.56
    as
    0.55
    SL
    0.54
    we
    0.54
    POSITIVE LOGITS
    ן
    0.61
    OutSize
    0.60
     инструментов
    0.60
    ।’
    0.59
    )।
    0.57
     monitored
    0.56
     инструменты
    0.55
    ຂອງ
    0.55
     voiced
    0.55
     ils
    0.53
    Activations Density 0.001%

    No Known Activations