© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1767
    Prev
    Next
    INDEX
    Explanations

    football teams and federations

    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_40_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
     temsil
    0.45
     棉
    0.45
    Peach
    0.43
     Avid
    0.39
    renerg
    0.38
    赭
    0.38
     Fort
    0.37
    Newman
    0.37
     predstav
    0.37
    橙
    0.36
    POSITIVE LOGITS
    മായും
    0.39
    CHN
    0.36
    )};
    0.34
     Visitation
    0.34
    Khe
    0.34
     工作
    0.34
    Workspace
    0.34
    !==
    0.33
    喀
    0.33
     López
    0.33
    Activations Density 0.005%

    No Known Activations