© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8772
    Prev
    Next
    INDEX
    Explanations

    text formatting directives in LaTeX

    oai_token-act-pair · gemini-2.0-flash

    scientific notations or terms

    np_token-act-pair-logits · gpt-4o-mini
    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
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.71
    $_['
    -0.68
    DebuggerStep
    -0.68
    :✨
    -0.67
    
    -0.67
     autorytatywna
    -0.66
    hyrchwyd
    -0.66
     otomatig
    -0.65
     &___
    -0.64
    vertising
    -0.62
    POSITIVE LOGITS
    ficamente
    0.45
    SequentialGroup
    0.44
    ول
    0.42
    тал
    0.41
    ↩
    0.41
     piec
    0.41
    ρεύ
    0.40
    assi
    0.40
    tal
    0.40
    ябрь
    0.40
    Activations Density 0.217%

    No Known Activations