© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29241
    Prev
    Next
    INDEX
    Explanations

    bombastic, flashy

    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
    ON
    0.93
    t
    0.93
    on
    0.89
     空
    0.79
    m
    0.79
    温泉
    0.79
    PE
    0.78
    l
    0.77
    get
    0.76
     Много
    0.75
    POSITIVE LOGITS
    :
    0.90
     qualcuno
    0.66
    이었다
    0.65
    ıları
    0.65
    ।
    0.65
     blandit
    0.63
    ী
    0.63
     accorded
    0.60
    ু
    0.60
    ыр
    0.59
    Activations Density 0.001%

    No Known Activations