© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9424
    Prev
    Next
    INDEX
    Explanations

    numbers, acronyms, and other code-like language peppered throughout the document

    oai_token-act-pair · gemini-2.0-flash

    scientific papers/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     VIAF
    -0.64
    égias
    -0.55
    ėja
    -0.55
     Paglinawan
    -0.51
    quels
    -0.51
     AssemblyCompany
    -0.50
    tså
    -0.49
    soever
    -0.48
    ceutical
    -0.48
     Gaut
    -0.47
    POSITIVE LOGITS
    apimachinery
    0.65
    UnsafeEnabled
    0.60
     فريبيس
    0.56
    omitempty
    0.54
    存于互联网档案馆
    0.52
    capa
    0.50
    бен
    0.50
    elk
    0.49
     tk
    0.48
    sizeCache
    0.48
    Activations Density 43.142%

    No Known Activations