© 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. 4188
    Prev
    Next
    INDEX
    Explanations

    lines of code syntax, specifically React.js.

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     ſou
    -0.78
    ſelves
    -0.78
    retudo
    -0.77
     Biôgrafia
    -0.77
     Houſe
    -0.77
     Exacts
    -0.74
     تضيفلها
    -0.73
     deere
    -0.73
     houſe
    -0.73
     auroit
    -0.71
    POSITIVE LOGITS
     to
    0.45
     “
    0.44
      
    0.44
     위해
    0.42
     et
    0.41
     local
    0.41
    ívne
    0.40
     or
    0.40
     ab
    0.40
     I
    0.39
    Activations Density 4.047%

    No Known Activations