© 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. 3683
    Prev
    Next
    INDEX
    Explanations

    words related to development, engineering, and medicine

    oai_token-act-pair · gemini-2.0-flash

    developing

    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
     developed
    -1.87
     developing
    -1.81
     develop
    -1.81
     develops
    -1.73
    developed
    -1.63
    developing
    -1.57
     DEVELOP
    -1.52
    develop
    -1.52
     Developed
    -1.50
    Developing
    -1.49
    POSITIVE LOGITS
    ParallelGroup
    0.76
     getItemCount
    0.61
     geslacht
    0.61
    DoubleQuotes
    0.60
    matchCondition
    0.60
     Domes
    0.59
     contenir
    0.58
    omla
    0.57
    forKey
    0.56
    jspb
    0.56
    Activations Density 11.805%

    No Known Activations