© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80455
    Prev
    Next
    INDEX
    Explanations

    words, punctuation, and special characters

    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_31_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
     еле
    0.42
    ategy
    0.39
     букмекеры
    0.38
     attentively
    0.38
    ལ
    0.38
     Element
    0.37
     Diagnostic
    0.36
     варто
    0.36
     بيد
    0.36
    ಬಹು
    0.35
    POSITIVE LOGITS
     immédi
    0.39
    haf
    0.38
    "]),
    0.38
    hift
    0.36
    workspaceFolder
    0.36
    ampang
    0.36
    괴
    0.36
    ர்த்த
    0.36
     ឬ
    0.35
    »),
    0.35
    Activations Density 0.000%

    No Known Activations