© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11135
    Prev
    Next
    INDEX
    Explanations

    text from scientific documents

    oai_token-act-pair · gemini-2.0-flash

    Chemical elements

    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
    клопе
    -0.59
    出版年
    -0.52
     elä
    -0.51
     IBOutlet
    -0.49
    AutoresizingMask
    -0.48
     excru
    -0.47
    PreferredItem
    -0.47
     ReSharper
    -0.46
     sedia
    -0.45
    省市镇
    -0.45
    POSITIVE LOGITS
     lead
    0.85
     zinc
    0.79
     Lead
    0.78
    Lead
    0.77
     stron
    0.74
     Stron
    0.74
     iron
    0.73
     carbon
    0.72
     mercury
    0.72
     silver
    0.71
    Activations Density 3.704%

    No Known Activations