© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18777
    Prev
    Next
    INDEX
    Explanations

    clubs and associations

    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
     ADN
    0.38
    종
    0.37
    ന്തര
    0.36
    пропетров
    0.35
    yong
    0.35
     DNA
    0.34
    分け
    0.34
    〠
    0.34
     Jong
    0.34
     Apo
    0.34
    POSITIVE LOGITS
     club
    2.25
     clubs
    2.09
    club
    2.02
     klub
    2.00
     क्लब
    1.98
    clubs
    1.90
     clube
    1.90
     клуб
    1.89
     клуба
    1.88
     clubes
    1.87
    Activations Density 0.021%

    No Known Activations