© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58951
    Prev
    Next
    INDEX
    Explanations

    unique or único

    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
    is
    0.72
    et
    0.65
    ine
    0.64
    વ
    0.63
    resident
    0.62
    #'
    0.60
     ujarnya
    0.60
    JP
    0.60
    Unter
    0.60
    isub
    0.59
    POSITIVE LOGITS
    。《
    0.63
     patty
    0.62
     crushing
    0.61
     pulver
    0.59
     reconciliation
    0.58
     käyt
    0.57
     токси
    0.57
    。
    0.57
     пу
    0.56
     shower
    0.56
    Activations Density 0.001%

    No Known Activations