© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2039
    Prev
    Next
    INDEX
    Explanations

    words and phrases in sports articles related to baseball and wrestling teams and the context around them

    oai_token-act-pair · gemini-2.0-flash

    Sports teams

    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
    bilden
    -0.47
    늘
    -0.43
    LIF
    -0.42
    itarian
    -0.42
     Universitaria
    -0.41
    致
    -0.41
    romos
    -0.41
     felici
    -0.41
    zerű
    -0.40
    ilius
    -0.40
    POSITIVE LOGITS
     propOrder
    0.81
     Италијани
    0.78
     initComponents
    0.78
     يتيمه
    0.66
     ThemeData
    0.63
    ernoo
    0.62
     ModelExpression
    0.62
     rebound
    0.61
     ddelweddau
    0.61
     الحره
    0.60
    Activations Density 0.767%

    No Known Activations