© 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. 7137
    Prev
    Next
    INDEX
    Explanations

    capital "S" at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    references to code or programming constructs

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

    Initials starting with S

    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
    Not in Any Lists

    No Comments

    Negative Logits
     remaining
    -0.54
    /******/
    -0.53
     appreciating
    -0.50
     individually
    -0.49
    timi
    -0.48
    tuta
    -0.48
    pædia
    -0.47
    tedly
    -0.47
     availability
    -0.47
     appreciation
    -0.47
    POSITIVE LOGITS
    ViewFeatures
    0.62
    MemoryWarning
    0.60
     saites
    0.57
     nakalista
    0.57
    invokeLater
    0.56
     betweenstory
    0.56
     sienta
    0.52
     estekak
    0.52
     StatelessWidget
    0.51
     BoxFit
    0.50
    Activations Density 0.277%

    No Known Activations