© 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. 121824
    Prev
    Next
    INDEX
    Explanations

    Barnaby's Big Escape

    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
    )
    0.86
    kannya
    0.70
     seasonings
    0.65
    )।
    0.64
    ką
    0.64
    ons
    0.61
    و
    0.61
    ो
    0.59
    каза
    0.59
     Solver
    0.59
    POSITIVE LOGITS
    t
    0.85
    h
    0.77
     တ
    0.77
    れる
    0.66
     cinco
    0.65
     S
    0.63
     하나님의
    0.63
     pernikahan
    0.62
     inglese
    0.62
     grandes
    0.61
    Activations Density 0.002%

    No Known Activations