© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14764
    Prev
    Next
    INDEX
    Explanations

    words strongly associated with medical or scientific research

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     include
    -0.37
    And
    -0.36
     And
    -0.35
     neod
    -0.35
    ç
    -0.35
    cos
    -0.34
    else
    -0.34
     entonces
    -0.33
     по
    -0.32
     &&
    -0.32
    POSITIVE LOGITS
    tagHelperRunner
    1.03
     ExecuteAsync
    0.88
     saying
    0.82
    makeConstraints
    0.82
    Obrázky
    0.81
    ConstraintMaker
    0.81
     BorderRadius
    0.81
    MessageTagHelper
    0.80
     GenerationType
    0.79
    saying
    0.77
    Activations Density 17.825%

    No Known Activations