© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8089
    Prev
    Next
    INDEX
    Explanations

    the cardinal directions, especially "Southern."

    oai_token-act-pair · gemini-2.0-flash

    Southern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    .
    -0.96
    ,
    -0.91
     
    -0.79
    k
    -0.76
    t
    -0.72
     in
    -0.71
    d
    -0.70
    h
    -0.70
      
    -0.68
    ing
    -0.68
    POSITIVE LOGITS
    BibitemShut
    1.36
    ViewImports
    1.30
     Monfieur
    1.26
    脚注の使い方
    1.25
     ་་
    1.23
    ^(@)
    1.22
    '}>
    1.22
     Мексичка
    1.22
     Audiodateien
    1.21
    bibfield
    1.20
    Activations Density 0.924%

    No Known Activations