© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7426
    Prev
    Next
    INDEX
    Explanations

    LaTeX math formulas

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Die
    -0.50
    IENTE
    -0.48
    imak
    -0.48
    sidemargin
    -0.47
    \|^{
    -0.46
    ніципа
    -0.46
    Étymologie
    -0.45
     PE
    -0.45
    ège
    -0.45
     Inc
    -0.45
    POSITIVE LOGITS
     armband
    0.70
     handker
    0.67
     Viceroy
    0.66
     Poincar
    0.65
     handkerchief
    0.65
     Magdalen
    0.64
     dimensionality
    0.64
     Pyrene
    0.64
     generalizations
    0.64
     Athenians
    0.64
    Activations Density 4.531%

    No Known Activations