© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15406
    Prev
    Next
    INDEX
    Explanations

    code-like text and mentions of medical or scientific terminology

    oai_token-act-pair · 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
    reportWebVitals
    -0.70
     uska
    -0.62
    ]")]
    -0.61
    الإنجليزية
    -0.61
    ształ
    -0.60
    AccessorTable
    -0.58
    vieve
    -0.56
    InvalidProtocol
    -0.55
    IsContent
    -0.55
    quelize
    -0.54
    POSITIVE LOGITS
     TC
    1.30
     T
    1.24
     TM
    1.21
     TG
    1.19
     Т
    1.18
     TP
    1.17
    TP
    1.16
     TJ
    1.16
     TD
    1.15
    TC
    1.14
    Activations Density 20.581%

    No Known Activations