© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11539
    Prev
    Next
    INDEX
    Explanations

    words related to vehicles and their parts, especially trucks and trailers

    oai_token-act-pair · gemini-2.0-flash

    Trucks and tractors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    PerformLayout
    -0.59
     ujednoznacz
    -0.58
    toMatchSnapshot
    -0.54
    XmlAccessType
    -0.52
    WebpackPlugin
    -0.49
    ngrx
    -0.47
    ništ
    -0.47
    FailureListener
    -0.46
    LikeLiked
    -0.46
    RegressionTest
    -0.46
    POSITIVE LOGITS
     truck
    0.87
     tractor
    0.73
     camion
    0.66
    truck
    0.66
     Truck
    0.66
     trucks
    0.65
    Truck
    0.64
     forklift
    0.63
     lorry
    0.62
     crane
    0.62
    Activations Density 1.708%

    No Known Activations