© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11750
    Prev
    Next
    INDEX
    Explanations

    words related to football plays and defensive actions

    oai_token-act-pair · gemini-2.0-flash

    intercepted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     setTimeout
    -0.50
     poveznice
    -0.44
     mengirimkan
    -0.43
     complètes
    -0.42
     envoie
    -0.42
    ngh
    -0.41
    tachten
    -0.41
     Huan
    -0.41
    gota
    -0.41
    estanden
    -0.40
    POSITIVE LOGITS
     Biôgrafia
    0.84
    expandindo
    0.81
    RenderAtEndOf
    0.73
    rungsseite
    0.71
     <>",
    0.70
     mergeFrom
    0.70
     propOrder
    0.66
    queryInterface
    0.66
    ConstraintMaker
    0.64
     unknownFields
    0.62
    Activations Density 0.595%

    No Known Activations