© 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. 4715
    Prev
    Next
    INDEX
    Explanations

    strings of numbers and punctuation marks, especially percentages

    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
    enterOuterAlt
    -1.03
    ValueStyle
    -0.96
    RegressionTest
    -0.95
    PerformLayout
    -0.94
     Италијани
    -0.92
     AssemblyProduct
    -0.91
    IUrlHelper
    -0.88
     purpoſe
    -0.88
    mybatisplus
    -0.86
     arşivlendi
    -0.83
    POSITIVE LOGITS
      
    0.48
    <eos>
    0.48
     common
    0.47
    TagHelpers
    0.45
    ↵↵
    0.45
    mayer
    0.44
    ,
    0.44
    nean
    0.43
     Sche
    0.43
     N
    0.42
    Activations Density 2.397%

    No Known Activations