© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10960
    Prev
    Next
    INDEX
    Explanations

    URLs and alphanumeric strings within URLs

    oai_token-act-pair · gemini-2.0-flash

    URLs

    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
    KommentareTeilen
    -0.73
    #![
    -0.60
    PARTMENT
    -0.56
    scalatest
    -0.50
     consultato
    -0.49
     danh
    -0.49
    avras
    -0.47
    +=
    -0.47
     lateinit
    -0.46
    CppMethod
    -0.46
    POSITIVE LOGITS
     NPA
    0.73
     autorytatywna
    0.73
    معلومات
    0.71
     AssemblyProduct
    0.69
     Baillargeon
    0.66
    foundland
    0.66
    :✨
    0.66
     GLC
    0.65
     ―――――
    0.64
    matorium
    0.64
    Activations Density 2.047%

    No Known Activations