© 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. 10938
    Prev
    Next
    INDEX
    Explanations

    words relating to aviation regulations and operation

    oai_token-act-pair · gemini-2.0-flash

    flying and aircraft operations

    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
    queryInterface
    -0.53
     fièvre
    -0.50
     CommonModule
    -0.49
    ParallelGroup
    -0.47
    XmlAccessorType
    -0.44
    Loss
    -0.44
    onets
    -0.44
     resourceCulture
    -0.43
    corrhi
    -0.42
    ์
    -0.42
    POSITIVE LOGITS
    RegressionTest
    0.80
     cdti
    0.69
     Jefus
    0.63
     myſelf
    0.63
     fubject
    0.60
     Efq
    0.60
     transfieras
    0.58
     AppColors
    0.58
     crdi
    0.57
    ſelf
    0.56
    Activations Density 1.836%

    No Known Activations