© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102514
    Prev
    Next
    INDEX
    Explanations

    fully qualified names or namespaces

    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_16_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
    gj
    0.58
    ニューヨーク
    0.57
    济
    0.55
    侨
    0.54
    梅
    0.54
    功率
    0.53
    gaxModule
    0.53
     sélectionnez
    0.53
    ጭ
    0.53
    drawString
    0.52
    POSITIVE LOGITS
     puberty
    0.64
     '
    0.52
    India
    0.52
     India
    0.51
     activity
    0.50
     infection
    0.49
    Sweden
    0.49
     modesty
    0.49
     mani
    0.49
     medically
    0.48
    Activations Density 0.000%

    No Known Activations