© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17025
    Prev
    Next
    INDEX
    Explanations

    sign in activity

    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_15_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
    ilim
    0.58
    maxx
    0.55
    ofield
    0.54
    oden
    0.53
     Romney
    0.53
    ⲟ
    0.53
     c
    0.52
     splitter
    0.52
     slaw
    0.51
    ilem
    0.51
    POSITIVE LOGITS
    기
    0.68
    Após
    0.63
    桃
    0.57
    立即
    0.54
    function
    0.53
    الت
    0.53
    ུ
    0.53
     Quando
    0.52
    ার
    0.51
    Dopo
    0.51
    Activations Density 0.000%

    No Known Activations