© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10735
    Prev
    Next
    INDEX
    Explanations

    text describing sports teams, particularly soccer

    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_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
    ChildScrollView
    -0.65
     team
    -0.63
    Team
    -0.61
     referenties
    -0.60
     Team
    -0.59
     teams
    -0.59
    チーム
    -0.57
     Roskov
    -0.56
     équipe
    -0.55
     الاطلاع
    -0.55
    POSITIVE LOGITS
    fromnode
    0.65
    RenderAtEndOf
    0.54
     <>",
    0.48
    matchCondition
    0.48
    lovakia
    0.47
    LabelTagHelper
    0.47
    TabStop
    0.46
     ErrIntOverflow
    0.46
    ربای
    0.46
     minOccurs
    0.46
    Activations Density 0.475%

    No Known Activations