© 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. 355
    Prev
    Next
    INDEX
    Explanations

    mentions of places "around the world" or scattered about a particular area

    oai_token-act-pair · gemini-2.0-flash

    Spatial prepositions

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    {§
    -0.56
    rawDesc
    -0.50
     getItemId
    -0.50
    principalColumn
    -0.49
    Hozzáférés
    -0.48
    tauscht
    -0.48
    casus
    -0.48
     متعلقه
    -0.47
    ISTRATION
    -0.47
    WAUKEE
    -0.47
    POSITIVE LOGITS
     throughout
    0.79
     partout
    0.77
    throughout
    0.77
     afield
    0.71
    Across
    0.69
    Throughout
    0.68
     around
    0.68
     across
    0.68
    Around
    0.67
     khắp
    0.66
    Activations Density 1.013%

    No Known Activations