© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9042
    Prev
    Next
    INDEX
    Explanations

    current time and date

    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_40_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
     циф
    0.37
     изд
    0.37
    曠
    0.37
     magnifying
    0.37
    dateFormat
    0.36
    elevationMap
    0.36
    plify
    0.35
    紛
    0.35
    ែ
    0.34
     รูป
    0.34
    POSITIVE LOGITS
    UTC
    0.95
     UTC
    0.89
    Local
    0.88
     local
    0.88
    local
    0.83
    LOCAL
    0.83
     Local
    0.79
     мест
    0.79
     UT
    0.79
     LOCAL
    0.78
    Activations Density 0.126%

    No Known Activations