© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9830
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to mathematical and scientific theories and models

    oai_token-act-pair · gemini-2.0-flash

    data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -0.66
     initComponents
    -0.65
    clusal
    -0.63
     OnTriggerEnter
    -0.62
    onnaissance
    -0.60
     CGSize
    -0.57
    fjspx
    -0.57
    OrWhiteSpace
    -0.57
    — 
    -0.56
     MotionEvent
    -0.56
    POSITIVE LOGITS
    thâu
    0.55
    <bos>
    0.49
     smooth
    0.48
     zag
    0.47
     resolve
    0.47
     AssemblyTitle
    0.46
     cod
    0.46
     both
    0.45
     Caves
    0.45
    Represent
    0.45
    Activations Density 3.506%

    No Known Activations