© 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. 11911
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in archeology and scientific analysis of historical times

    oai_token-act-pair · gemini-2.0-flash

    archeology

    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
     ↑
    -0.44
    ^{-}$
    -0.37
    ใส
    -0.34
     espir
    -0.33
    padu
    -0.33
     custos
    -0.33
     Bund
    -0.32
     "\
    -0.32
    行き
    -0.32
    habilit
    -0.32
    POSITIVE LOGITS
    expandindo
    0.96
    tagHelperRunner
    0.91
    reportWebVitals
    0.87
    تقاوى
    0.85
    writeFieldEnd
    0.85
    SharedDtor
    0.85
    BASEPATH
    0.82
    Geplaatst
    0.80
    sidemargin
    0.80
     Савезне
    0.79
    Activations Density 1.661%

    No Known Activations