© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125889
    Prev
    Next
    INDEX
    Explanations

    Alan, Anís, Nin

    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
    ä
    0.96
    i
    0.87
     i
    0.76
    '
    0.75
    ang
    0.69
     construction
    0.68
     $
    0.68
    ו
    0.68
    ಿ
    0.67
     can
    0.67
    POSITIVE LOGITS
    с
    0.72
    ন
    0.68
    з
    0.67
    ны
    0.66
    li
    0.64
    ます
    0.64
    IENT
    0.63
    DETAIL
    0.63
    lenül
    0.62
    이지만
    0.61
    Activations Density 0.000%

    No Known Activations