© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12441
    Prev
    Next
    INDEX
    Explanations

    mentions of sports champions and player injuries

    oai_token-act-pair · gemini-2.0-flash

    Sports news and opinion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    vább
    -0.57
     onCreateView
    -0.56
    ifolium
    -0.48
    acres
    -0.48
     Thon
    -0.47
    가
    -0.47
     accesso
    -0.47
    llium
    -0.46
     natin
    -0.46
    ipot
    -0.46
    POSITIVE LOGITS
    parsedMessage
    0.81
     يتيمه
    0.71
     للاسماء
    0.67
    enderror
    0.59
    بوابة
    0.57
    
    0.57
     صوتيه
    0.56
    tagHelperRunner
    0.55
    Datuak
    0.54
    Portale
    0.52
    Activations Density 0.267%

    No Known Activations