© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10451
    Prev
    Next
    INDEX
    Explanations

    technical language found in scientific literature relating to immune response, cancer, and genetics

    oai_token-act-pair · gemini-2.0-flash

    inflammation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     propOrder
    -0.63
    DataAnnotations
    -0.63
     समीक्षक
    -0.59
    ValueStyle
    -0.56
    rungsseite
    -0.56
     übrig
    -0.52
     fantasma
    -0.50
    addSubview
    -0.50
     podrob
    -0.49
    CppCodeGen
    -0.47
    POSITIVE LOGITS
     inflammation
    0.59
     Wikimedijinoj
    0.55
     referenties
    0.54
     signal
    0.53
     apoptosis
    0.52
     cellular
    0.49
    lado
    0.49
    prechpartner
    0.48
    ostasis
    0.47
    ровок
    0.47
    Activations Density 6.863%

    No Known Activations