© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91419
    Prev
    Next
    INDEX
    Explanations

    High Likelihood, Upfront Cost

    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_3_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
    ر
    0.77
    с
    0.73
    ar
    0.71
    س
    0.68
    racht
    0.67
    िंग
    0.67
    r
    0.67
    lier
    0.66
    uating
    0.66
    ل
    0.66
    POSITIVE LOGITS
    ك
    0.77
    ↵
    0.72
     është
    0.70
    k
    0.69
    ח
    0.67
    Median
    0.62
    ش
    0.62
    ને
    0.62
    Widgets
    0.61
    Density
    0.61
    Activations Density 0.003%

    No Known Activations