© 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. 126943
    Prev
    Next
    INDEX
    Explanations

    sveltejs code / paths

    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
    м
    0.71
    וש
    0.70
    ة
    0.66
    ي
    0.65
    ات
    0.64
    يب
    0.62
     moet
    0.61
    تو
    0.60
     erforderlich
    0.60
    지고
    0.59
    POSITIVE LOGITS
    in
    0.74
    і
    0.71
    of
    0.71
    ị
    0.70
    е
    0.68
     were
    0.68
    公司
    0.67
     zwią
    0.67
    ä
    0.67
     şirk
    0.66
    Activations Density 0.000%

    No Known Activations