© 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. 13010
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and names that relate to healthcare and medicine

    oai_token-act-pair · gemini-2.0-flash

    save

    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
    enumi
    -0.65
    Hentet
    -0.42
    υγ
    -0.42
    autoreleasepool
    -0.41
     cref
    -0.41
    evos
    -0.41
    Примітки
    -0.40
     Brexit
    -0.40
    υμ
    -0.40
     Explor
    -0.40
    POSITIVE LOGITS
     saving
    1.93
     saved
    1.88
     save
    1.78
     saves
    1.73
     Saving
    1.64
    Saving
    1.61
    saving
    1.59
    saves
    1.55
     Save
    1.54
    save
    1.53
    Activations Density 6.243%

    No Known Activations