© 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. 38479
    Prev
    Next
    INDEX
    Explanations

    driving innovation

    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
    ten
    0.98
    ri
    0.76
    i
    0.73
    are
    0.71
    ta
    0.70
    the
    0.68
    li
    0.67
    ting
    0.66
    ford
    0.66
    ts
    0.66
    POSITIVE LOGITS
    ل
    0.71
    ت
    0.63
    руса
    0.61
    你
    0.61
    :
    0.59
    鎿
    0.57
    抓住
    0.57
    ...
    0.56
    يكية
    0.56
     Bernadette
    0.56
    Activations Density 0.048%

    No Known Activations