© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7380
    Prev
    Next
    INDEX
    Explanations

    passages discussing player selection and tactics within a sports team

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
    ScopeManager
    -0.74
    styleType
    -0.68
    parsedMessage
    -0.68
    iastes
    -0.57
    AddTagHelper
    -0.57
    GEBURTSDATUM
    -0.56
     kaarangay
    -0.56
    issory
    -0.54
    KommentareTeilen
    -0.54
     dAtA
    -0.54
    POSITIVE LOGITS
    geführten
    0.56
     vectorielles
    0.54
     maintien
    0.50
    zaamheid
    0.45
    erialize
    0.45
     zufolge
    0.44
     disponibilités
    0.44
     Millard
    0.43
    chik
    0.43
    führen
    0.43
    Activations Density 1.481%

    No Known Activations