© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10614
    Prev
    Next
    INDEX
    Explanations

    computer code and medical terms related to oxygen levels

    oai_token-act-pair · gemini-2.0-flash

    o

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ibos
    -0.57
     esternos
    -0.52
     SafeMath
    -0.50
    AnchorStyles
    -0.50
    Hochspringen
    -0.49
    UserScript
    -0.48
    HtmlAttribute
    -0.48
     estekak
    -0.47
    rungsseite
    -0.47
    mybatisplus
    -0.47
    POSITIVE LOGITS
    ///</
    0.67
    principalTable
    0.60
    Còn
    0.56
    arot
    0.52
     themſelves
    0.50
     ruota
    0.49
     leſs
    0.49
     سكانية
    0.48
    PhysRev
    0.48
    στό
    0.48
    Activations Density 5.407%

    No Known Activations