© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8572
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to government alerts, specifically missile alerts

    oai_token-act-pair · gemini-2.0-flash

    missile/launch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     nahilalakip
    -0.69
    ⓧ
    -0.59
     disponibilités
    -0.59
    kháu
    -0.54
    tanleria
    -0.54
    chartInstance
    -0.53
    oara
    -0.51
     iNdEx
    -0.50
    toMatchSnapshot
    -0.50
    zczy
    -0.49
    POSITIVE LOGITS
     missiles
    0.89
     missile
    0.84
     rockets
    0.77
     launch
    0.75
     rocket
    0.75
     launcher
    0.73
     Launch
    0.71
     launchers
    0.71
     miss
    0.69
     launches
    0.69
    Activations Density 1.011%

    No Known Activations