© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222602
    Prev
    Next
    INDEX
    Explanations

    collection and gathering

    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
    1
    0.69
     from
    0.68
     with
    0.64
    6
    0.63
    sp
    0.62
    o
    0.62
    a
    0.61
    pping
    0.61
    <0x0D>
    0.57
    pe
    0.56
    POSITIVE LOGITS
    ка
    1.08
    ك
    1.04
    ра
    0.81
    كا
    0.71
    كار
    0.70
    нути
    0.68
     и
    0.66
     و
    0.65
     व
    0.64
    тина
    0.63
    Activations Density 0.007%

    No Known Activations