© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1940
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · 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
    
    -0.63
    IsMutable
    -0.61
    NameInMap
    -0.58
    ArrowToggle
    -0.56
     Winaray
    -0.54
     Caspar
    -0.54
     Boug
    -0.53
    addCriterion
    -0.53
    contentLoaded
    -0.52
    LayoutStyle
    -0.52
    POSITIVE LOGITS
    Egypt
    0.68
     Egy
    0.66
     Egypt
    0.63
     المصرية
    0.60
    Egy
    0.60
    GenerationType
    0.56
    viewDidLoad
    0.55
     UnityEngine
    0.55
     egip
    0.54
     Egyptian
    0.54
    Activations Density 3.617%

    No Known Activations