© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1202
    Prev
    Next
    INDEX
    Explanations

    mentions of Canada, medical or legal terms, and locations.

    oai_token-act-pair · gemini-2.0-flash

    Canada, Australia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Australian
    -1.45
     Canadian
    -1.42
    Australian
    -1.36
     Australia
    -1.34
    Canadian
    -1.31
     Canada
    -1.30
    Australia
    -1.25
    Canada
    -1.18
     Canadians
    -1.16
     Aussie
    -1.13
    POSITIVE LOGITS
     Савезне
    0.82
    :✨
    0.73
    MLLoader
    0.68
    épend
    0.67
    bollah
    0.62
     utafitiHapana
    0.60
     Chwiliwch
    0.59
     */;
    0.59
    endpush
    0.57
    aryen
    0.57
    Activations Density 11.978%

    No Known Activations