© 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. 13154
    Prev
    Next
    INDEX
    Explanations

    phrases commonly used to write persuasively in research papers and legal documents

    oai_token-act-pair · gemini-2.0-flash

    proposals

    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
     ویکی‌پدی
    -0.68
     CreateTagHelper
    -0.61
    DoubleQuotes
    -0.59
     myſelf
    -0.57
    ExecuteReader
    -0.56
    évaluateur
    -0.54
     verdicts
    -0.53
    URLConnection
    -0.53
    ilitate
    -0.52
     preuve
    -0.51
    POSITIVE LOGITS
     put
    1.19
     pro
    1.14
     prop
    0.99
     Put
    0.98
     presented
    0.97
     Pro
    0.97
    Put
    0.96
    put
    0.94
    pro
    0.91
     advanced
    0.89
    Activations Density 3.118%

    No Known Activations