© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3787
    Prev
    Next
    INDEX
    Explanations

    scientific and medical texts

    oai_token-act-pair · gemini-2.0-flash

    specialized medical terms or disease classifications

    np_token-act-pair-logits · gpt-4o-mini

    medical case reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Revenir
    -0.56
     BoxDecoration
    -0.55
    ibol
    -0.54
    WriteTagHelper
    -0.52
    Erfolge
    -0.52
     AssemblyVersion
    -0.52
    enciales
    -0.50
    PhysRevLett
    -0.50
     libera
    -0.48
    bbers
    -0.47
    POSITIVE LOGITS
    DeleteBehavior
    0.80
     Biôgrafia
    0.61
    Rohy
    0.59
    queryInterface
    0.57
     дописавши
    0.55
     صوتيه
    0.51
    $_['
    0.50
     مرئيه
    0.50
     تضيفلها
    0.49
    ModelBuilder
    0.49
    Activations Density 7.846%

    No Known Activations