© 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. 7461
    Prev
    Next
    INDEX
    Explanations

    locations such as cities, schools, and avenues, as well as the preposition "in"

    oai_token-act-pair · gemini-2.0-flash

    Locations

    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
    HtmlAttribute
    -0.68
    VersionUID
    -0.68
    IsContent
    -0.61
     ModelExpression
    -0.58
     sas
    -0.57
    ArrowToggle
    -0.56
     geslacht
    -0.54
    SharedDtor
    -0.52
    Milit
    -0.52
    WithIdentifier
    -0.52
    POSITIVE LOGITS
     leçons
    0.64
     mères
    0.63
     définiti
    0.60
     prisonniers
    0.59
     âmes
    0.59
     pères
    0.58
    ftagPool
    0.58
     européennes
    0.56
     rigue
    0.55
     ennemis
    0.55
    Activations Density 1.580%

    No Known Activations