© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12961
    Prev
    Next
    INDEX
    Explanations

    references to American sports, specifically football and baseball

    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
     متعلقه
    -0.63
    SequentialGroup
    -0.63
    CloseOperation
    -0.57
    hmig
    -0.54
    ReusableCell
    -0.52
    ForRow
    -0.52
    laag
    -0.52
     homes
    -0.51
    )++;
    -0.51
     JpaRepository
    -0.50
    POSITIVE LOGITS
    Rhestr
    0.59
    addCriterion
    0.53
    UnusedPrivate
    0.52
    Viungo
    0.48
     Мексичка
    0.48
     disambiguazione
    0.48
     Vorm
    0.48
    WebServlet
    0.48
    EDEFAULT
    0.48
    PRWEB
    0.47
    Activations Density 1.075%

    No Known Activations