© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180389
    Prev
    Next
    INDEX
    Explanations

    sports team achievements and titles

    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_24_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
     Thailand
    0.40
     および
    0.39
     Stalin
    0.37
     아닌
    0.37
     Bismarck
    0.37
     `<=
    0.36
     समर्थक
    0.36
     (`
    0.35
     Stadium
    0.35
     фактор
    0.35
    POSITIVE LOGITS
    िवा
    0.38
    ங்கு
    0.35
    ოვ
    0.35
    রিদ্র
    0.34
    vođa
    0.33
     perpetuated
    0.33
     boarding
    0.33
     tradiz
    0.33
    Lint
    0.32
     wink
    0.32
    Activations Density 0.000%

    No Known Activations