© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12837
    Prev
    Next
    INDEX
    Explanations

    references to Australia

    oai_token-act-pair · gemini-2.0-flash

    Australia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Australia
    -2.02
     Australian
    -1.88
    Australia
    -1.74
    Australian
    -1.71
     Australians
    -1.64
     AUSTRALIA
    -1.62
     australia
    -1.53
     australian
    -1.51
     Austr
    -1.51
     Aussie
    -1.49
    POSITIVE LOGITS
     تضيفلها
    0.88
    IGraphics
    0.65
    MigrationBuilder
    0.56
     normaux
    0.56
     vectorielles
    0.55
    évaluateur
    0.54
     traseira
    0.52
    ┑
    0.51
     henvisninger
    0.51
     Amérique
    0.50
    Activations Density 2.159%

    No Known Activations