© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15236
    Prev
    Next
    INDEX
    Explanations

    NFL football

    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_34_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
     Strawberry
    0.41
     strawberry
    0.39
    strawberry
    0.38
    cust
    0.37
    熔
    0.37
    カット
    0.37
     Mediation
    0.36
    衲
    0.36
     মেড
    0.35
     Solvent
    0.35
    POSITIVE LOGITS
     NFL
    0.84
    NFL
    0.74
    🏈
    0.63
     football
    0.62
    football
    0.57
     फुटबॉल
    0.55
     Redskins
    0.54
     футбо
    0.52
     Football
    0.50
    Football
    0.50
    Activations Density 0.030%

    No Known Activations