© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4367
    Prev
    Next
    INDEX
    Explanations

    place names - cities, countries, and regions

    oai_token-act-pair · gemini-2.0-flash

    Geographical locations

    np_max-act · gemini-2.0-flash

    island names

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    <bos>
    -0.75
    
    -0.60
     region
    -0.56
    '
    -0.54
    畿
    -0.49
    parseColor
    -0.48
     Region
    -0.48
     sahaja
    -0.47
     countries
    -0.47
    Gu
    -0.46
    POSITIVE LOGITS
     nakalista
    0.83
     للاسماء
    0.83
     NSCoder
    0.78
    RenderAtEndOf
    0.78
     متعلقه
    0.76
    AccessorTable
    0.75
     propOrder
    0.71
    SharedDtor
    0.70
     فريبيس
    0.69
     وتسجيلات
    0.69
    Activations Density 1.203%

    No Known Activations