© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2887
    Prev
    Next
    INDEX
    Explanations

    source code, comments, and meeting agendas

    oai_token-act-pair · gemini-2.0-flash

    parentheses and "statements"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ChildScrollView
    -0.61
     nakalista
    -0.57
    BeginContext
    -0.56
    
    -0.56
    UTERS
    -0.56
    chartInstance
    -0.52
     SafeMath
    -0.51
    <bos>
    -0.50
    ynchronously
    -0.49
     Potomac
    -0.49
    POSITIVE LOGITS
    TagMode
    0.86
     AppCompatTheme
    0.66
    Hochspringen
    0.48
    aspectj
    0.48
     InputDecoration
    0.48
    ForValue
    0.47
    出版年
    0.47
     ffilmiau
    0.46
    Архівовано
    0.46
     مرئيه
    0.46
    Activations Density 9.815%

    No Known Activations