© 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. 4906
    Prev
    Next
    INDEX
    Explanations

    phrases related to Egyptian imagery, in particular related to the Book of Ra.

    oai_token-act-pair · gemini-2.0-flash

    Egypt

    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
     Egyptian
    -1.67
    Egyptian
    -1.54
     Egypt
    -1.54
    Egypt
    -1.40
     EGYPT
    -1.37
     Egyptians
    -1.34
     Cairo
    -1.30
     Egipto
    -1.23
     Egyp
    -1.20
     egip
    -1.18
    POSITIVE LOGITS
     ExecuteAsync
    0.67
     <>",
    0.47
    Aria
    0.47
    :✨
    0.47
     Aria
    0.46
    isLoaded
    0.45
    σθ
    0.45
    Kir
    0.45
    pok
    0.44
    Amen
    0.44
    Activations Density 1.152%

    No Known Activations