© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54351
    Prev
    Next
    INDEX
    Explanations

    function/code block structure

    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_31_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
     jednocześnie
    0.37
     minori
    0.35
     સરળ
    0.35
     Petrus
    0.34
    ᱮ
    0.34
    湿
    0.34
    Calculating
    0.34
     estoque
    0.34
     simultaneously
    0.32
     完成
    0.32
    POSITIVE LOGITS
     cuyos
    0.38
    isance
    0.36
    occup
    0.33
    镌
    0.33
     ocup
    0.33
     dalších
    0.33
    idler
    0.33
    Occup
    0.32
    していきます
    0.31
    wast
    0.31
    Activations Density 0.003%

    No Known Activations