© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102020
    Prev
    Next
    INDEX
    Explanations

    to whom it may concern

    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_14_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
    א
    0.66
    ಮ
    0.64
    スト
    0.63
    म
    0.62
    is
    0.59
    ي
    0.58
    i
    0.58
    as
    0.57
    for
    0.57
    י
    0.57
    POSITIVE LOGITS
    GlobalSection
    0.61
    𒌍
    0.58
    ését
    0.55
    nın
    0.54
     रझा
    0.54
    navList
    0.53
     Там
    0.52
    Scalars
    0.52
     seguinte
    0.52
    ný
    0.52
    Activations Density 0.000%

    No Known Activations