© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1167
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to narrative storytelling, especially dialogue and internal monologue

    oai_token-act-pair · gemini-2.0-flash

    Story/novel excerpts

    np_max-act-logits · gemini-2.0-flash
    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
    ValueStyle
    -0.78
    :✨
    -0.72
    delwed
    -0.66
     surprised
    -0.64
     puzzled
    -0.63
     amazed
    -0.62
    ыгана
    -0.61
     GENERATED
    -0.60
    hésitez
    -0.60
     CreateTagHelper
    -0.60
    POSITIVE LOGITS
    ThroughAttribute
    0.64
    :\/\/
    0.50
    
    0.47
    seteq
    0.46
    ordu
    0.43
    ۪
    0.43
    parsedMessage
    0.42
     Prime
    0.42
    django
    0.41
     exchange
    0.41
    Activations Density 1.145%

    No Known Activations