© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36525
    Prev
    Next
    INDEX
    Explanations

    held themselves

    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_11_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
     ।
    0.62
    бав
    0.62
    a
    0.59
    gesamt
    0.58
    ानंतर
    0.57
    ="|
    0.56
    ;
    0.56
    सेल
    0.56
    водится
    0.55
    し
    0.55
    POSITIVE LOGITS
     M
    0.59
     Yakima
    0.59
     bourbon
    0.56
     prodig
    0.55
     carriera
    0.55
     January
    0.55
     patrimonio
    0.54
     amarillo
    0.53
     Kilim
    0.53
     niektórych
    0.52
    Activations Density 0.000%

    No Known Activations