© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58751
    Prev
    Next
    INDEX
    Explanations

    degree `d` polynomials

    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_11_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
    ct
    0.62
    ors
    0.60
    text
    0.59
     i
    0.59
    ries
    0.58
    ov
    0.57
    $
    0.57
    but
    0.56
    rv
    0.56
    0.55
    POSITIVE LOGITS
     különb
    0.61
     bilirubin
    0.59
     gstlal
    0.57
    。【
    0.57
     فِي
    0.57
     Zustimmung
    0.57
    见面
    0.56
    ᇂ
    0.56
    чної
    0.55
     maximization
    0.55
    Activations Density 0.016%

    No Known Activations