© 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. 93049
    Prev
    Next
    INDEX
    Explanations

    tennis serve, net, court, fault, rally

    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
    ème
    0.40
    ógico
    0.39
    Á
    0.37
    CI
    0.36
    ćeg
    0.35
    VA
    0.33
    aría
    0.33
    YS
    0.32
    ará
    0.31
    rá
    0.31
    POSITIVE LOGITS
     peur
    0.32
     tokoh
    0.32
     kdy
    0.32
     skl
    0.32
     caiu
    0.32
     kuasa
    0.31
     పోటీ
    0.31
    ,*
    0.31
     *>
    0.31
     ছাত্রী
    0.31
    Activations Density 0.002%

    No Known Activations