© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4577
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments

    oai_token-act-pair · gemini-2.0-flash

    LaTeX 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    بوابة
    -0.58
     jScrollPane
    -0.57
    tonode
    -0.57
     okuyayım
    -0.55
     GenerationType
    -0.54
     Chwiliwch
    -0.52
    StoreMessageInfo
    -0.50
    pida
    -0.50
    DialogTitle
    -0.49
    ikyuu
    -0.49
    POSITIVE LOGITS
    المكان
    0.57
    кономі
    0.56
     Référence
    0.51
     vœux
    0.50
    slidesToShow
    0.49
    getHeaders
    0.48
    RSpec
    0.46
    setzungen
    0.46
    исленность
    0.46
    ModelBuilder
    0.45
    Activations Density 0.040%

    No Known Activations