© 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. 7268
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to bone fractures and injuries, specifically in a medical context

    oai_token-act-pair · gemini-2.0-flash

    bone, bones, broken

    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
     Cordero
    -0.59
     aught
    -0.56
    epam
    -0.50
    élica
    -0.48
    forRoot
    -0.48
    cain
    -0.47
     AssemblyCulture
    -0.47
     jungle
    -0.47
    riceps
    -0.47
    oquia
    -0.46
    POSITIVE LOGITS
     bones
    1.01
     bone
    0.99
     Bone
    0.89
    bone
    0.88
    骨
    0.85
    bones
    0.84
    Bone
    0.81
     Bones
    0.81
    BONE
    0.78
    Bones
    0.73
    Activations Density 0.690%

    No Known Activations