© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14363
    Prev
    Next
    INDEX
    Explanations

    square brackets

    oai_token-act-pair · gemini-2.0-flash

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    verwijspagina
    -0.58
     ")[
    -0.48
    op
    -0.47
    "){
    -0.47
     ')[
    -0.46
    D
    -0.46
    '){
    -0.46
    "){
    -0.46
     De
    -0.45
     bo
    -0.45
    POSITIVE LOGITS
     itſelf
    0.92
     Jefus
    0.88
     Majefty
    0.88
     pleaſure
    0.87
     himſelf
    0.83
     themſelves
    0.83
     Efq
    0.83
     Monfieur
    0.82
     Anſ
    0.81
     Theſe
    0.81
    Activations Density 3.202%

    No Known Activations