© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1736
    Prev
    Next
    INDEX
    Explanations

    scientific papers and their citations related to proteins and cells.

    oai_token-act-pair · gemini-2.0-flash

    biology research

    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
     
    -0.48
    jooq
    -0.43
     No
    -0.43
     vuông
    -0.42
     later
    -0.41
     später
    -0.41
     das
    -0.41
     Force
    -0.39
     en
    -0.38
     no
    -0.38
    POSITIVE LOGITS
    PerformLayout
    1.00
    setVerticalGroup
    0.99
    StoryboardSegue
    0.95
    ViewImports
    0.93
     AspNetCore
    0.93
     '\\;'
    0.89
    MigrationBuilder
    0.88
    UnusedPrivate
    0.85
    RetentionPolicy
    0.82
     AssemblyProduct
    0.81
    Activations Density 2.218%

    No Known Activations