© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15778
    Prev
    Next
    INDEX
    Explanations

    mentions of Dukes, Duchesses and other Aristocracy related terms

    oai_token-act-pair · gemini-2.0-flash

    noble titles and families

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    
    -0.60
    ⓘ
    -0.53
    出版年
    -0.50
    ArgumentParser
    -0.47
    Hochspringen
    -0.46
     Texts
    -0.46
    opsida
    -0.46
     brady
    -0.46
     hyperplasia
    -0.45
     Iranian
    -0.45
    POSITIVE LOGITS
    antMatchers
    0.70
    StructEnd
    0.70
     ujednoznacz
    0.68
    spesies
    0.61
     resourceCulture
    0.60
    Cyfeiriadau
    0.59
    XmlAccessType
    0.56
     متعلقه
    0.56
    twimg
    0.54
    Personendaten
    0.54
    Activations Density 0.631%

    No Known Activations