© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11590
    Prev
    Next
    INDEX
    Explanations

    words related to sport and game outcomes

    oai_token-act-pair · gemini-2.0-flash

    Rugby

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rugby
    -0.83
    Rugby
    -0.78
     rugby
    -0.73
     cricket
    -0.65
     Cricket
    -0.63
    Cricket
    -0.61
    Erstellt
    -0.58
    rugby
    -0.57
     football
    -0.54
     Colony
    -0.52
    POSITIVE LOGITS
     Spring
    0.72
    Spring
    0.67
     SPRING
    0.55
    ']>;
    0.53
    횟
    0.52
    SupportActionBar
    0.52
     HomeController
    0.50
    gezogen
    0.50
    CLASSES
    0.50
    NewUrlParser
    0.49
    Activations Density 2.666%

    No Known Activations