© 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. 13752
    Prev
    Next
    INDEX
    Explanations

    parentheses, exponents, the article "the", "on", phone contact information, and "confidence", seeming to focus on mathematical contexts

    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
     IG
    -0.98
     IR
    -0.96
     IC
    -0.93
     IM
    -0.87
     ICC
    -0.84
     IW
    -0.84
     IP
    -0.83
     IE
    -0.83
     ig
    -0.83
     Irons
    -0.83
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    Према
    0.70
     Waray
    0.67
    expandindo
    0.64
     Signalez
    0.62
    Chham
    0.60
     Públicas
    0.59
     Paglinawan
    0.59
     Administrativna
    0.57
     JAXBElement
    0.56
    Activations Density 0.604%

    No Known Activations