© 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-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6091
    Prev
    Next
    INDEX
    Explanations

    words related to the FIFA World Cup and soccer

    oai_token-act-pair · gemini-2.0-flash

    sporting events and tournaments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    StoryboardSegue
    -1.02
     utafitiHapana
    -0.72
    oredCriteria
    -0.68
     internetowa
    -0.66
    ="@+
    -0.66
    bootstrapcdn
    -0.65
     мәкал
    -0.65
     فريبيس
    -0.63
     FontWeight
    -0.63
    RegistryLite
    -0.62
    POSITIVE LOGITS
    band
    0.47
     group
    0.46
     passes
    0.46
    rag
    0.45
    modium
    0.45
     dej
    0.44
     band
    0.43
    Passes
    0.43
     passing
    0.42
     passed
    0.42
    Activations Density 0.404%

    No Known Activations