© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14011
    Prev
    Next
    INDEX
    Explanations

    dialogue and associated punctuation in narrative scenes

    oai_token-act-pair · gemini-2.0-flash

    royalty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     للاسماء
    -0.71
     <=",
    -0.62
    windowFixed
    -0.56
     bílé
    -0.54
     saites
    -0.53
     määrä
    -0.53
    WebVitals
    -0.52
    idencial
    -0.48
    ProcessEvent
    -0.47
    UALA
    -0.47
    POSITIVE LOGITS
     الاطلاع
    0.56
    ourge
    0.55
    ConverterFactory
    0.52
    slavery
    0.52
    reactstrap
    0.51
    indeed
    0.50
    rikes
    0.49
    hető
    0.48
    oxone
    0.48
    hartt
    0.48
    Activations Density 0.222%

    No Known Activations