© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63242
    Prev
    Next
    INDEX
    Explanations

    HTML opening tag

    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
    (“
    0.39
    朋
    0.38
    穵
    0.37
     ایل
    0.36
    Ը
    0.36
     בח
    0.34
    ()),
    0.34
     вывод
    0.34
    -<
    0.34
    ״
    0.34
    POSITIVE LOGITS
     Ol
    0.84
    Ol
    0.77
     ol
    0.76
    ol
    0.73
    OL
    0.59
     OL
    0.50
    olai
    0.46
    keyList
    0.46
     p
    0.45
    noof
    0.43
    Activations Density 0.001%

    No Known Activations