© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232732
    Prev
    Next
    INDEX
    Explanations

    choose

    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
    有点
    0.40
    संग
    0.39
    ยิน
    0.38
    有點
    0.38
    冒
    0.38
     ред
    0.38
     duidelijk
    0.37
     одно
    0.37
    ሆ
    0.37
     яв
    0.37
    POSITIVE LOGITS
     choice
    0.66
    choice
    0.57
     scelta
    0.54
     choix
    0.50
     choices
    0.50
     Choices
    0.50
     CHOICE
    0.48
    Choice
    0.47
     Choice
    0.46
     keuze
    0.46
    Activations Density 0.002%

    No Known Activations