© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99526
    Prev
    Next
    INDEX
    Explanations

    Rome, Court, Chapel, Saving History

    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_14_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
    ﺝ
    0.62
    tDBOutput
    0.61
     حصہ
    0.57
    >());
    0.56
    DanhMucSP
    0.55
     ใบ
    0.55
     బై
    0.55
    ти
    0.54
    يده
    0.54
    getMainUI
    0.54
    POSITIVE LOGITS
    document
    0.66
    well
    0.65
    0.59
    er
    0.58
    le
    0.56
    en
    0.55
    body
    0.54
    u
    0.54
    domain
    0.53
    i
    0.53
    Activations Density 0.000%

    No Known Activations