© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1690
    Prev
    Next
    INDEX
    Explanations

    legal jargon and references to specific companies or places involved in legal disputes

    oai_token-act-pair · gemini-2.0-flash

    company names

    np_max-act-logits · gemini-2.0-flash

    Century

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    LabelTagHelper
    -0.74
     Phry
    -0.66
    ]='\
    -0.65
     <>",
    -0.63
    isContained
    -0.63
     eventdata
    -0.62
    IUrlHelper
    -0.59
     Мексичка
    -0.59
     resourceCulture
    -0.58
     jaundice
    -0.58
    POSITIVE LOGITS
     Network
    0.54
     National
    0.53
     Ar
    0.50
    Ar
    0.50
     Coast
    0.49
    Linq
    0.48
     West
    0.47
     World
    0.47
     Américas
    0.47
     Court
    0.46
    Activations Density 2.369%

    No Known Activations