© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44929
    Prev
    Next
    INDEX
    Explanations

    sleep well

    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_3_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
    ä
    0.80
     disabilities
    0.75
    8
    0.73
    ls
    0.72
    لی
    0.71
    ला
    0.70
    ↵
    0.68
     networks
    0.66
    </h3>
    0.65
    .',
    0.65
    POSITIVE LOGITS
     KPI
    0.77
    ي
    0.72
     بيان
    0.70
    يء
    0.70
    喤
    0.69
    <0x80>
    0.68
    цию
    0.66
     تعريف
    0.66
    i
    0.66
    يته
    0.66
    Activations Density 0.008%

    No Known Activations