© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12155
    Prev
    Next
    INDEX
    Explanations

    the country Canada with decreasing activation for related words, such as the adjective 'Canadian' and the city 'Toronto'

    oai_token-act-pair · gemini-2.0-flash

    Canada

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Canada
    -1.50
     Canadian
    -1.50
    Canadian
    -1.44
    Canada
    -1.42
    <bos>
    -1.31
     Canadians
    -1.26
     CANADA
    -1.15
     Canadá
    -1.12
     canada
    -1.09
    加拿大
    -1.05
    POSITIVE LOGITS
     resourceCulture
    0.84
     rootReducer
    0.80
     snippetHide
    0.79
    tvguidetime
    0.79
    Datuak
    0.77
    cellaneous
    0.76
    expandindo
    0.74
     endian
    0.74
     MainAxisSize
    0.74
    
    0.73
    Activations Density 0.711%

    No Known Activations