© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62407
    Prev
    Next
    INDEX
    Explanations

    tennis and related sports

    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_41_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
    :].
    0.38
     பை
    0.38
    orylation
    0.36
    閣
    0.35
    𖤐
    0.35
    }^{\
    0.35
     أوروبا
    0.35
     высокую
    0.35
     пос
    0.35
    回収
    0.34
    POSITIVE LOGITS
     tennis
    1.14
    tennis
    1.01
     Tennis
    1.00
    Tennis
    0.99
     tenis
    0.96
     टेनिस
    0.91
     Wimbledon
    0.80
     lawn
    0.80
     теннис
    0.78
    🎾
    0.77
    Activations Density 0.001%

    No Known Activations