© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34042
    Prev
    Next
    INDEX
    Explanations

    shapes and descriptors

    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
     queda
    0.70
     تھا۔
    0.64
    ме
    0.63
    ەك
    0.62
    ى
    0.61
     cottura
    0.61
    。
    0.60
    ي
    0.60
     ہے۔
    0.59
     چاہیے۔
    0.58
    POSITIVE LOGITS
    t
    0.93
    0.78
    d
    0.74
    으로
    0.69
    ud
    0.68
    ag
    0.67
    的小
    0.66
    '
    0.65
    dependent
    0.64
    ide
    0.64
    Activations Density 0.023%

    No Known Activations