© 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. 11929
    Prev
    Next
    INDEX
    Explanations

    articles discussing accidents, policing, and vehicle chases on roadways.

    oai_token-act-pair · gemini-2.0-flash

    Car accidents and police

    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
     }}"></
    -0.58
    !("{}",
    -0.52
    printStackTrace
    -0.49
     parkir
    -0.46
    liğini
    -0.46
    llywood
    -0.46
    ευ
    -0.45
     volta
    -0.45
    ImageList
    -0.44
    ulka
    -0.44
    POSITIVE LOGITS
     beginnetje
    0.96
     transfieras
    0.73
     ProtoMessage
    0.72
    Personensuche
    0.71
     estekak
    0.69
    SourceChecksum
    0.66
     ویکی‌پدی
    0.63
     transférez
    0.63
     >=",
    0.63
    :✨
    0.63
    Activations Density 1.053%

    No Known Activations