© 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. 3317
    Prev
    Next
    INDEX
    Explanations

    a mix of scientific terms, names of people and mathematical formatting

    oai_token-act-pair · 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
     blevet
    -0.40
    IUrlHelper
    -0.39
     tématu
    -0.38
     fleste
    -0.38
    ↵↵
    -0.38
    ството
    -0.38
     Emits
    -0.37
    ParallelGroup
    -0.37
     sure
    -0.36
     protoimpl
    -0.36
    POSITIVE LOGITS
    出版年
    1.00
    findpost
    0.78
     Signalez
    0.77
    Zeneca
    0.74
    PerformLayout
    0.68
     iſt
    0.68
     <>",
    0.68
    WithIOException
    0.67
     cdti
    0.65
     мәкал
    0.64
    Activations Density 0.557%

    No Known Activations