© 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. 36531
    Prev
    Next
    INDEX
    Explanations

    erratic behavior

    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
    ata
    0.91
    .],
    0.62
     폐
    0.59
     Agriculture
    0.59
    attiyam
    0.58
    ATE
    0.58
     einem
    0.57
    ቿ
    0.57
     Derivatives
    0.57
     Apparel
    0.57
    POSITIVE LOGITS
    lilik
    0.54
    lions
    0.52
    konto
    0.51
    நீர்
    0.51
    kunde
    0.50
    inou
    0.49
    ْم
    0.49
    ေါ်
    0.49
    సుకోవ
    0.47
    LIBRARY
    0.47
    Activations Density 0.001%

    No Known Activations