© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202831
    Prev
    Next
    INDEX
    Explanations

    chance

    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_46_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
    こう
    0.40
    QQ
    0.38
     అను
    0.38
     orada
    0.37
     مبت
    0.37
    職
    0.37
     ill
    0.37
     literate
    0.36
    類
    0.36
     suivante
    0.35
    POSITIVE LOGITS
    increases
    0.41
     increase
    0.40
     diminu
    0.40
     foreclosure
    0.39
     increases
    0.39
     Increase
    0.39
    ewall
    0.39
     aumento
    0.38
     INCRE
    0.38
    Increase
    0.38
    Activations Density 0.002%

    No Known Activations