© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10153
    Prev
    Next
    INDEX
    Explanations

    language related to religious ritual, especially in the context of the Old Testament

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     resourceCulture
    -0.74
     متعلقه
    -0.70
    новниш
    -0.70
     défaite
    -0.69
    SourceChecksum
    -0.66
     viewType
    -0.65
    WindowConstants
    -0.65
    سطس
    -0.64
     Demographics
    -0.64
    Sucesor
    -0.64
    POSITIVE LOGITS
    yttää
    0.41
     vuitton
    0.36
    꽁
    0.36
     asses
    0.36
    GEBURTSDATUM
    0.35
     inoxidable
    0.34
    icoot
    0.33
     aged
    0.33
    __":
    0.32
    хан
    0.32
    Activations Density 0.914%

    No Known Activations