© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147462
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    al
    0.68
    to
    0.46
    for
    0.44
    AL
    0.44
    including
    0.42
    alık
    0.41
    neſs
    0.41
    >|</
    0.39
    re
    0.38
     excit
    0.38
    POSITIVE LOGITS
    ad
    0.62
    int
    0.49
    a
    0.44
     int
    0.43
    া
    0.42
    +
    0.41
     martin
    0.40
     ad
    0.39
    ing
    0.39
    اد
    0.38
    Activations Density 0.010%

    No Known Activations