© 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. 206255
    Prev
    Next
    INDEX
    Explanations

    assignment or initialization and values

    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
    ორი
    0.90
    it
    0.89
    ن
    0.84
    ش
    0.82
     université
    0.82
     in
    0.80
     alimentaire
    0.79
    ون
    0.78
    기
    0.77
     विश्वविद्यालय
    0.77
    POSITIVE LOGITS
     value
    1.18
    Value
    1.06
    ค่า
    1.04
    value
    1.03
     değeri
    1.02
     hodnot
    1.01
    0
    1.00
     Value
    0.98
     değer
    0.94
    Values
    0.91
    Activations Density 0.011%

    No Known Activations