© 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. 223513
    Prev
    Next
    INDEX
    Explanations

    URLs with doi.org

    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
    ك
    0.89
     و
    0.87
     ά
    0.84
    τα
    0.83
     άλλ
    0.82
     υπάρχ
    0.76
    :
    0.76
    ذا
    0.74
     що
    0.72
    ↵↵
    0.71
    POSITIVE LOGITS
    umbling
    0.72
    ad
    0.71
    z
    0.70
    opoulos
    0.70
    ati
    0.68
    o
    0.68
    संस्करण
    0.67
    r
    0.67
    Config
    0.64
    mountain
    0.64
    Activations Density 0.001%

    No Known Activations