© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34217
    Prev
    Next
    INDEX
    Explanations

    Yasser, Yasuo, Jassy, Alammar

    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
    는
    0.94
    ل
    0.86
    나
    0.82
    是
    0.77
    ת
    0.76
    고
    0.75
    は
    0.74
    什么
    0.71
    на
    0.70
    一
    0.69
    POSITIVE LOGITS
    5
    0.84
    4
    0.73
     Stav
    0.63
    articolo
    0.63
     for
    0.63
    ুব
    0.63
     Cabot
    0.63
     bak
    0.62
    ARS
    0.62
     Developer
    0.61
    Activations Density 0.002%

    No Known Activations