© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163817
    Prev
    Next
    INDEX
    Explanations

    macao and com

    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_13_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
    ی
    0.58
     τότε
    0.52
    تان
    0.50
     ядер
    0.49
     потен
    0.48
     тариф
    0.48
     زمان
    0.48
    ᱐
    0.48
     промышленности
    0.47
     آزمایش
    0.46
    POSITIVE LOGITS
     Booker
    0.50
    Controller
    0.49
    X
    0.48
     Dutch
    0.47
    IMS
    0.47
    OPS
    0.46
    ROLE
    0.46
    R
    0.46
    Doctors
    0.46
    Dutch
    0.45
    Activations Density 0.000%

    No Known Activations