© 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. 225523
    Prev
    Next
    INDEX
    Explanations

    jsdelivr cdn links

    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
    z
    0.75
    k
    0.73
    де
    0.70
     haute
    0.68
    Kitchen
    0.66
    xiety
    0.65
    PP
    0.63
    f
    0.62
    PAR
    0.61
    eyes
    0.61
    POSITIVE LOGITS
    <0xA7>
    0.79
     Через
    0.76
    나
    0.75
    <0x81>
    0.74
    <0xAD>
    0.73
    {//
    0.73
    na
    0.71
    <0x9B>
    0.66
     डेढ़
    0.65
    是
    0.65
    Activations Density 0.000%

    No Known Activations