© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27474
    Prev
    Next
    INDEX
    Explanations

    widget, beetle, or technical widgets

    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_10_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
    is
    0.79
    as
    0.71
    of
    0.64
    in
    0.64
    it
    0.61
    ش
    0.57
    ro
    0.56
    In
    0.56
    ")
    0.56
    are
    0.55
    POSITIVE LOGITS
    жной
    0.54
    сить
    0.51
     Hasil
    0.50
    ט
    0.49
    ের
    0.49
     کمک
    0.48
     نمی‌
    0.48
     MacK
    0.48
     T
    0.47
     SizedBox
    0.47
    Activations Density 0.000%

    No Known Activations