© 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. 13806
    Prev
    Next
    INDEX
    Explanations

    topics related to New Zealand, specifically indigenous people and nature conservation

    oai_token-act-pair · gemini-2.0-flash

    Maori/New Zealand related

    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
     Australian
    -0.63
     Australia
    -0.59
    Australia
    -0.56
     AUSTRALIA
    -0.54
    Australie
    -0.54
    Australian
    -0.54
     australiano
    -0.51
    Jeografia
    -0.49
    脚注の使い方
    -0.49
    complexContent
    -0.48
    POSITIVE LOGITS
     Maori
    0.69
    ThroughAttribute
    0.66
     Māori
    0.65
     Southland
    0.64
    Ota
    0.60
     Taran
    0.60
    nz
    0.59
     Rang
    0.57
    Christ
    0.57
     kau
    0.57
    Activations Density 0.214%

    No Known Activations