© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1884
    Prev
    Next
    INDEX
    Explanations

    "both of which," "all of which," or "each of which" phrases

    oai_token-act-pair · gemini-2.0-flash

    Quantifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    TagMode
    -0.88
    LabelTagHelper
    -0.87
     utafitiHapana
    -0.82
    зулта
    -0.82
    webElementXpaths
    -0.76
    IsMutable
    -0.71
    IContainer
    -0.71
    ThroughAttribute
    -0.70
    InitVars
    -0.70
     propOrder
    -0.69
    POSITIVE LOGITS
     nhau
    0.50
    Jedis
    0.48
     hóa
    0.43
     bev
    0.43
    selves
    0.43
    ach
    0.41
     port
    0.40
    nv
    0.39
    각
    0.39
    times
    0.38
    Activations Density 1.597%

    No Known Activations