© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3393
    Prev
    Next
    INDEX
    Explanations

    a mix of Chinese characters, SEO terms, and references to Chinese geography or history

    oai_token-act-pair · gemini-2.0-flash

    Code snippets/foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    
    -0.51
     Cy
    -0.44
     PO
    -0.44
     Sy
    -0.44
    ,...
    -0.43
     RO
    -0.42
     Ro
    -0.42
    ia
    -0.42
     Ole
    -0.41
     AA
    -0.41
    POSITIVE LOGITS
    spreis
    0.77
    ssysteme
    0.75
     aveug
    0.75
     religieuses
    0.74
    skosten
    0.73
     voisins
    0.71
     funkce
    0.70
     fidèles
    0.70
     مرئيه
    0.69
     africains
    0.69
    Activations Density 20.145%

    No Known Activations