© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6404
    Prev
    Next
    INDEX
    Explanations

    computer code and error messages

    oai_token-act-pair · gemini-2.0-flash

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.77
     itſelf
    -1.06
     themſelves
    -1.00
     Monfieur
    -0.91
     himſelf
    -0.90
     Theſe
    -0.90
     myſelf
    -0.88
     raiſ
    -0.86
     pleaſure
    -0.85
     initComponents
    -0.79
    POSITIVE LOGITS
     ["
    0.51
     "
    0.50
    setVerticalGroup
    0.50
     [
    0.50
     many
    0.48
     ['
    0.47
     же
    0.47
     $
    0.47
     pula
    0.47
     '
    0.47
    Activations Density 1.698%

    No Known Activations