© 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. 50686
    Prev
    Next
    INDEX
    Explanations

    product description

    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
    ل
    0.93
     operands
    0.82
     curvatures
    0.79
     изделий
    0.77
     Fleurit
    0.77
    ម្លៃ
    0.76
    емых
    0.75
    тна
    0.74
    最优
    0.72
     deformations
    0.72
    POSITIVE LOGITS
    D
    1.06
    2
    0.99
    ;
    0.98
     June
    0.91
    B
    0.87
    RO
    0.85
    OR
    0.85
     December
    0.83
    T
    0.83
    SE
    0.82
    Activations Density 0.006%

    No Known Activations