© 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. 35920
    Prev
    Next
    INDEX
    Explanations

    come on

    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
    i
    0.89
    a
    0.75
    V
    0.63
    iD
    0.61
    o
    0.61
    W
    0.61
    is
    0.61
    N
    0.61
     d
    0.56
    d
    0.56
    POSITIVE LOGITS
     Полу
    0.64
     তীব্র
    0.63
     Коро
    0.63
     Да
    0.63
     Неза
    0.63
    auc
    0.62
     Ра
    0.60
     Ко
    0.59
     Тран
    0.59
    кт
    0.59
    Activations Density 0.000%

    No Known Activations