© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12950
    Prev
    Next
    INDEX
    Explanations

    code, import statements, commenting, the copyright symbol, numbers, and parenthesis

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ddelweddau
    -0.70
     kasarigan
    -0.68
    AddTagHelper
    -0.68
    aarrggbb
    -0.60
    RegressionTest
    -0.57
    CrossRef
    -0.57
     gynhyrchwyd
    -0.56
    ignées
    -0.54
    
    -0.53
    WithIOException
    -0.53
    POSITIVE LOGITS
    \<^
    0.69
    BRUARY
    0.68
    ouſly
    0.65
     BRARY
    0.65
     RSITY
    0.65
    ICAGO
    0.63
    BRARY
    0.62
    IFORNIA
    0.61
    elfare
    0.60
    INTENANCE
    0.60
    Activations Density 1.059%

    No Known Activations