© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9718
    Prev
    Next
    INDEX
    Explanations

    words related to code, proteins, DNA, and cells in scientific literature

    oai_token-act-pair · gemini-2.0-flash

    biochemistry/biology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     propOrder
    -0.95
     ModelExpression
    -0.87
    findpost
    -0.81
    ThroughAttribute
    -0.80
     disambiguazione
    -0.79
     betweenstory
    -0.79
    DockStyle
    -0.78
    batore
    -0.77
    WithIOException
    -0.77
    ScopeManager
    -0.76
    POSITIVE LOGITS
    Jereo
    0.60
     gug
    0.55
     pop
    0.52
     toto
    0.51
     baby
    0.51
     Jr
    0.50
     neither
    0.50
     "
    0.50
    titious
    0.50
    bebe
    0.50
    Activations Density 1.915%

    No Known Activations