© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3269
    Prev
    Next
    INDEX
    Explanations

    words related to health, medicine, and scientific/biological research

    oai_token-act-pair · gemini-2.0-flash

    medicine/biology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AccessorTable
    -0.71
    IndentedString
    -0.69
     BorderRadius
    -0.69
    queryInterface
    -0.68
     createSlice
    -0.68
    PreferredItem
    -0.65
    parsedMessage
    -0.61
    исленность
    -0.60
    verwijspagina
    -0.58
    richTextPanel
    -0.57
    POSITIVE LOGITS
     Determin
    0.55
    γε
    0.55
     Asegúrese
    0.52
    ียง
    0.51
    turnstile
    0.50
     ACTION
    0.49
    utschen
    0.48
     Pili
    0.48
    pincode
    0.48
     dispensary
    0.48
    Activations Density 2.124%

    No Known Activations