© 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. 11912
    Prev
    Next
    INDEX
    Explanations

    language around treating cardiac arrest with defibrillation

    oai_token-act-pair · gemini-2.0-flash

    external

    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
     transparence
    -0.60
     виправивши
    -0.59
    Transparency
    -0.58
    DoubleQuotes
    -0.57
    middels
    -0.54
    ("]");
    -0.53
     Assyrian
    -0.52
    ربای
    -0.52
     casada
    -0.52
     levé
    -0.51
    POSITIVE LOGITS
    AccessorTable
    0.68
    ProgressHUD
    0.56
    GeneratedCode
    0.50
    tahui
    0.49
     pão
    0.48
     PagesJaunes
    0.48
    hynch
    0.47
    DotNetBar
    0.47
     patent
    0.47
    ussis
    0.47
    Activations Density 0.629%

    No Known Activations