© 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. 89077
    Prev
    Next
    INDEX
    Explanations

    if needed

    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
    k
    0.73
    correct
    0.62
    rs
    0.59
    response
    0.59
    din
    0.59
    Y
    0.59
    been
    0.57
    sufficient
    0.57
    return
    0.56
    i
    0.56
    POSITIVE LOGITS
    ม
    0.64
     publicação
    0.63
     modulo
    0.61
    म
    0.61
    ต
    0.59
     aka
    0.59
     mł
    0.59
     vě
    0.58
     quá
    0.57
     AKA
    0.57
    Activations Density 0.003%

    No Known Activations