© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13054
    Prev
    Next
    INDEX
    Explanations

    content related to news and broadcast television

    oai_token-act-pair · gemini-2.0-flash

    network

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Watching
    -0.78
    Watch
    -0.75
     Watch
    -0.75
     Watches
    -0.74
     watch
    -0.73
     watching
    -0.71
    watch
    -0.70
     WATCH
    -0.70
    Watching
    -0.69
    WATCH
    -0.65
    POSITIVE LOGITS
     network
    0.66
    DoubleQuotes
    0.57
    cast
    0.57
    network
    0.57
    Network
    0.51
    zae
    0.50
     Network
    0.50
     Chwiliwch
    0.49
    casting
    0.48
    Fiche
    0.48
    Activations Density 1.081%

    No Known Activations