© 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. 36287
    Prev
    Next
    INDEX
    Explanations

    act of intervening or intervening

    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
    re
    0.58
    T
    0.57
    ber
    0.55
    is
    0.54
    ki
    0.54
     kini
    0.54
    ka
    0.53
    sl
    0.53
     heart
    0.52
    आई
    0.51
    POSITIVE LOGITS
     polinom
    0.75
    ك
    0.69
    تالي
    0.68
     Quadrupèdes
    0.68
    $:
    0.66
    الس
    0.66
     ascertaining
    0.65
    
    0.65
    ات
    0.65
    тят
    0.65
    Activations Density 0.003%

    No Known Activations