© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194784
    Prev
    Next
    INDEX
    Explanations

    Emin Gün Sirer

    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_9_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
    im
    0.70
     ወይም
    0.69
     adsorb
    0.69
    s
    0.69
    ک
    0.67
     latérales
    0.65
    தி
    0.63
     нагрузки
    0.62
     оказались
    0.62
    regon
    0.61
    POSITIVE LOGITS
     son
    0.52
    creen
    0.52
    lette
    0.51
     te
    0.50
     مردم
    0.48
    fish
    0.47
    header
    0.46
     Members
    0.46
    悰
    0.46
     senate
    0.46
    Activations Density 0.000%

    No Known Activations