© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1079
    Prev
    Next
    INDEX
    Explanations

    words that come from scientific or historical texts

    oai_token-act-pair · gemini-2.0-flash

    scientific/historical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Rojas
    -0.62
    PhysRev
    -0.60
    ppb
    -0.56
     kiss
    -0.54
    
    -0.53
     buro
    -0.52
    gypti
    -0.51
    PSL
    -0.50
     sesso
    -0.50
    بية
    -0.50
    POSITIVE LOGITS
    تقاوى
    0.93
    ंदीखरीदारी
    0.93
    IndentedString
    0.89
    发表于
    0.85
    ).</
    0.83
    aarrggbb
    0.81
    EndInit
    0.79
    Personensuche
    0.74
     незавершена
    0.73
    ItemBackground
    0.73
    Activations Density 7.032%

    No Known Activations