© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13812
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in tax-related contexts

    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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     nahilalakip
    -0.77
    حياتها
    -0.67
     estekak
    -0.64
    viewDidLoad
    -0.63
    NUMX
    -0.61
    حياته
    -0.60
     genomen
    -0.60
    RenderAtEndOf
    -0.60
     foon
    -0.60
    PageIndex
    -0.59
    POSITIVE LOGITS
     Australian
    0.75
     Australia
    0.66
    Australian
    0.62
     Brisbane
    0.58
     Canberra
    0.57
     Aussie
    0.56
    Australia
    0.55
     Queensland
    0.54
     AUSTR
    0.54
     Aus
    0.53
    Activations Density 26.587%

    No Known Activations