© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3109
    Prev
    Next
    INDEX
    Explanations

    football player names

    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_39_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
     британ
    0.52
     Брита
    0.45
     영국
    0.44
    雇
    0.44
     যুক্তরাজ
    0.42
    英國
    0.42
    🏊
    0.42
    🏈
    0.41
     Britons
    0.41
     ব্রিটেন
    0.40
    POSITIVE LOGITS
     defender
    0.46
    omen
    0.43
     Tavern
    0.42
    ckie
    0.42
     substitute
    0.42
     creator
    0.42
     unmarked
    0.41
     wing
    0.41
    kiy
    0.41
     defenders
    0.40
    Activations Density 0.016%

    No Known Activations