© 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. 50438
    Prev
    Next
    INDEX
    Explanations

    Tailwind CSS

    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
    м
    0.88
    к
    0.69
     зво
    0.68
     الل
    0.65
    н
    0.65
    𝑟
    0.63
     примене
    0.63
     dźwię
    0.62
     govori
    0.62
     activeButton
    0.61
    POSITIVE LOGITS
    aj
    0.65
    ensburg
    0.63
    ais
    0.61
    {
    0.60
    ubes
    0.59
     Students
    0.58
     Ethnicity
    0.58
    U
    0.58
     students
    0.57
    uelles
    0.57
    Activations Density 0.006%

    No Known Activations