© 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. 40046
    Prev
    Next
    INDEX
    Explanations

    forgo or make

    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
     réflex
    0.64
    л
    0.64
     ядер
    0.63
     réponses
    0.62
    ะ
    0.62
     табли
    0.61
     WED
    0.61
    il
    0.60
    (´
    0.60
     tại
    0.59
    POSITIVE LOGITS
    v
    0.77
    city
    0.75
    kou
    0.75
    n
    0.69
    marine
    0.68
    ką
    0.64
    man
    0.63
    craft
    0.62
    ve
    0.62
    kant
    0.61
    Activations Density 0.000%

    No Known Activations