© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4300
    Prev
    Next
    INDEX
    Explanations

    text related to medical or dental contexts, including dentures, resorption, and patients

    oai_token-act-pair · gemini-2.0-flash

    medical/dental texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    BeginContext
    -0.72
    Ecotoxicity
    -0.68
     écout
    -0.61
     déchir
    -0.56
    ￣)
    -0.56
     okuyayım
    -0.56
     privilégi
    -0.55
    Kaieteur
    -0.55
     culturelles
    -0.55
    cipar
    -0.54
    POSITIVE LOGITS
    hul
    0.54
    wz
    0.53
     Bar
    0.53
     bar
    0.50
    BarItem
    0.50
     arch
    0.50
     bari
    0.47
    hock
    0.46
     Arch
    0.46
    uellement
    0.46
    Activations Density 0.730%

    No Known Activations