© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15517
    Prev
    Next
    INDEX
    Explanations

    latex code snippets

    oai_token-act-pair · gemini-2.0-flash

    brackets and includegraphics commands

    np_token-act-pair-logits · gpt-4o-mini

    [

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    endphp
    -1.08
     '\\;'
    -1.06
     bezeichneter
    -1.01
    ThroughAttribute
    -0.95
     autorytatywna
    -0.93
     <=",
    -0.93
    aarrggbb
    -0.93
     Мексичка
    -0.90
    PerformLayout
    -0.87
    TagMode
    -0.87
    POSITIVE LOGITS
     
    0.61
    vin
    0.59
     at
    0.58
     T
    0.54
     (
    0.51
     no
    0.51
    igh
    0.50
     a
    0.50
     A
    0.50
    ina
    0.48
    Activations Density 0.104%

    No Known Activations