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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10822
    Prev
    Next
    INDEX
    Explanations

    words related to Pacific Islander ethnicity and culture

    oai_token-act-pair · gemini-2.0-flash

    Pacific Islands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Malawi
    -0.60
     typelib
    -0.57
     oignon
    -0.56
     Congo
    -0.54
    Geplaatst
    -0.54
     cebola
    -0.53
    angular
    -0.51
    Varint
    -0.50
    enegal
    -0.50
    Congo
    -0.50
    POSITIVE LOGITS
     gainera
    0.60
    transQ
    0.54
     Sam
    0.54
    findpost
    0.52
    imat
    0.52
    ratos
    0.51
     виправивши
    0.51
    tgz
    0.51
    anair
    0.50
    expandindo
    0.50
    Activations Density 0.776%

    No Known Activations