© 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. 36724
    Prev
    Next
    INDEX
    Explanations

    Hungarian, Basque, Russian, German

    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
     пли
    0.62
     пла
    0.59
     су
    0.59
     ф
    0.54
     место
    0.54
     йо
    0.53
     apropi
    0.52
     ח
    0.52
     primeiro
    0.51
     první
    0.50
    POSITIVE LOGITS
    normal
    0.70
    a
    0.62
    mild
    0.59
    vres
    0.59
    gen
    0.58
    sin
    0.58
    hash
    0.58
    some
    0.58
    wide
    0.57
    ssh
    0.57
    Activations Density 0.003%

    No Known Activations