© 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. 27510
    Prev
    Next
    INDEX
    Explanations

    ставиьте, where, Laboratory, Dou, tableView

    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
    ية
    0.74
    ти
    0.69
    。
    0.66
     jeopard
    0.66
     erred
    0.66
     ★★
    0.66
    çin
    0.66
     ৩
    0.64
     ۶
    0.64
     d
    0.64
    POSITIVE LOGITS
    Response
    0.67
    u
    0.65
    transmission
    0.64
    t
    0.59
    was
    0.58
    y
    0.57
    Transmission
    0.57
    ências
    0.56
    g
    0.55
    This
    0.55
    Activations Density 0.000%

    No Known Activations