© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3833
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and associated terminology

    oai_token-act-pair · gemini-2.0-flash

    Linear algebra/matrices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    aarrggbb
    -0.60
    onomi
    -0.55
     OFDb
    -0.54
    cplusplus
    -0.53
    nsito
    -0.52
     Lexer
    -0.51
     Cabral
    -0.51
     initComponents
    -0.50
    bua
    -0.50
    خوان
    -0.48
    POSITIVE LOGITS
     Houſe
    0.70
     houſe
    0.68
     Diſ
    0.62
     itſelf
    0.62
     ſeveral
    0.60
    ContentAsync
    0.57
     Reſ
    0.56
    verwijspagina
    0.56
     ſtate
    0.55
     reaſon
    0.54
    Activations Density 7.970%

    No Known Activations