© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5062
    Prev
    Next
    INDEX
    Explanations

    words related to medical trials and treatment effectiveness

    oai_token-act-pair · gemini-2.0-flash

    Study results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    uwu
    -0.55
    loroethane
    -0.55
    gata
    -0.52
     Macau
    -0.49
    itonitis
    -0.48
    Segoe
    -0.48
     covenants
    -0.47
    fortunate
    -0.47
    LUT
    -0.46
    ガニック
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.62
    CodedInputStream
    0.62
     CreateTagHelper
    0.58
     signif
    0.54
     ویکی‌پدی
    0.54
     désolés
    0.54
    Демографія
    0.54
    providedIn
    0.53
     effectiveness
    0.52
    protoimpl
    0.52
    Activations Density 3.912%

    No Known Activations