© 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. 36757
    Prev
    Next
    INDEX
    Explanations

    Block and sorting algorithms

    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
    若
    0.57
    அ
    0.54
    場合
    0.52
    ௦
    0.50
    бра
    0.50
    し
    0.50
    之
    0.48
     Ferien
    0.47
    піль
    0.46
    腾讯
    0.46
    POSITIVE LOGITS
     .
    0.53
    for
    0.50
    ad
    0.49
     seawater
    0.49
     birth
    0.48
     moistur
    0.47
    writer
    0.46
     moisturizing
    0.45
     anchor
    0.45
     dryness
    0.45
    Activations Density 0.000%

    No Known Activations