© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7291
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to physics and chemistry

    oai_token-act-pair · gemini-2.0-flash

    physics concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     rate
    -0.42
     dem
    -0.42
    prech
    -0.41
    示
    -0.40
    pushd
    -0.40
     Art
    -0.40
    ranch
    -0.39
     cal
    -0.39
     stock
    -0.38
     hay
    -0.38
    POSITIVE LOGITS
    
    0.73
    MemoryWarning
    0.72
     referenties
    0.71
     Lázaro
    0.69
     NSCoder
    0.69
     ComVisible
    0.68
    HasAnnotation
    0.68
    Hochspringen
    0.68
     ſever
    0.67
     itſelf
    0.67
    Activations Density 0.926%

    No Known Activations