© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12675
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to biological molecules and processes

    oai_token-act-pair · gemini-2.0-flash

    amino acids

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ItemLayout
    -0.54
    lotte
    -0.52
     pH
    -0.49
    фициальный
    -0.48
     uns
    -0.48
     Besar
    -0.47
     opposite
    -0.46
    bello
    -0.46
     firſt
    -0.46
     Khalil
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.78
    makeConstraints
    0.71
    AndEndTag
    0.70
    styleType
    0.70
    ConstraintMaker
    0.69
    complexContent
    0.66
    setVerticalGroup
    0.65
     disambiguazione
    0.63
     CURLOPT
    0.62
     propOrder
    0.62
    Activations Density 2.300%

    No Known Activations