© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89329
    Prev
    Next
    INDEX
    Explanations

    Nadia, Nadella, Comăneci

    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
    is
    0.92
    c
    0.92
    ле
    0.73
    ко
    0.73
    ри
    0.70
    э
    0.70
    cular
    0.68
    cısı
    0.68
    cations
    0.68
    зыка
    0.67
    POSITIVE LOGITS
    I
    0.93
    ä
    0.89
    1
    0.81
    İ
    0.77
    CASE
    0.76
    BD
    0.75
    K
    0.74
    GL
    0.73
    YS
    0.71
    SB
    0.71
    Activations Density 0.001%

    No Known Activations