© 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. 223584
    Prev
    Next
    INDEX
    Explanations

    source type

    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
    عی
    0.94
    ختی
    0.92
    لین
    0.86
    اریخ
    0.81
    σον
    0.79
    عنی
    0.77
    خواه
    0.77
    変
    0.77
    ва
    0.76
    ولی
    0.76
    POSITIVE LOGITS
    de
    0.89
    t
    0.88
    .
    0.78
    *
    0.74
     as
    0.68
    d
    0.66
    <
    0.64
    st
    0.64
    ↵
    0.63
    4
    0.61
    Activations Density 0.000%

    No Known Activations