© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12246
    Prev
    Next
    INDEX
    Explanations

    a mix of DNA sequences with 'CAA', movie characters from what appears to be Thailand, and legal terms or personal titles, making it hard to summarize into a single unified concept

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.87
     propOrder
    -0.80
    SequentialGroup
    -0.80
     typelib
    -0.74
     تضيفلها
    -0.70
    enderror
    -0.69
    AndEndTag
    -0.68
     Italijani
    -0.67
    ContentAsync
    -0.66
     AssemblyTitle
    -0.65
    POSITIVE LOGITS
    ̯
    0.68
     Waterways
    0.61
    τώ
    0.60
     pravi
    0.59
    PIE
    0.59
     QUERY
    0.59
     Yew
    0.59
     Aimee
    0.57
     Brodie
    0.56
     auss
    0.56
    Activations Density 2.192%

    No Known Activations