© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7973
    Prev
    Next
    INDEX
    Explanations

    words involved in sports commentary, especially regarding Manchester United and Manchester City

    oai_token-act-pair · gemini-2.0-flash

    sports, management, 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    }{*}{}
    -0.54
     wireType
    -0.52
    AppCompat
    -0.52
     numerus
    -0.52
     World
    -0.52
    diq
    -0.51
    IVERY
    -0.50
    Geplaatst
    -0.50
    piercing
    -0.49
    onActivityResult
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.60
    MemoryWarning
    0.56
     étan
    0.49
    ConstraintMaker
    0.48
    Eksterne
    0.48
     graphiques
    0.47
     particulier
    0.46
     hjäl
    0.46
     revanche
    0.45
    ArrowToggle
    0.45
    Activations Density 1.050%

    No Known Activations