© 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. 12805
    Prev
    Next
    INDEX
    Explanations

    words referring to chemical compounds and phytochemical analysis

    oai_token-act-pair · gemini-2.0-flash

    Biochemistry and metabolites

    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
    AccessorTable
    -0.70
    تقاوى
    -0.59
    findpost
    -0.58
    Autoritní
    -0.57
    ruptedException
    -0.57
    全文
    -0.57
    AutoScale
    -0.57
    testens
    -0.56
     élect
    -0.56
    __*/
    -0.55
    POSITIVE LOGITS
    ArrowToggle
    0.54
    Jeografia
    0.53
    Tembelea
    0.49
     cler
    0.48
     Himo
    0.47
    ifrance
    0.47
     repeal
    0.47
     parch
    0.46
     mang
    0.46
    atecas
    0.45
    Activations Density 1.257%

    No Known Activations