© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3952
    Prev
    Next
    INDEX
    Explanations

    terms related to soccer, Trinidad, injuries and medicine.

    oai_token-act-pair · gemini-2.0-flash

    Trinidad/Tobago Football

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ModelExpression
    -0.55
    Ibid
    -0.55
    Autoritní
    -0.51
     Quint
    -0.51
     écoulé
    -0.50
    FieldBuilder
    -0.50
    paux
    -0.49
    HtmlAttribute
    -0.49
     CreateTagHelper
    -0.49
     Merle
    -0.48
    POSITIVE LOGITS
    ArgsConstructor
    0.63
    AndEndTag
    0.57
    ConstraintMaker
    0.56
    ✨:
    0.54
     forKey
    0.54
    writeField
    0.53
    BURGH
    0.52
     Pittsburgh
    0.50
    phemy
    0.50
     viewDidLoad
    0.50
    Activations Density 4.250%

    No Known Activations