© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6376
    Prev
    Next
    INDEX
    Explanations

    opinionated statements about something being of very high quality/degree or significance, and some references to government.

    oai_token-act-pair · gemini-2.0-flash

    best

    np_max-act · gemini-2.0-flash

    best

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ImageContext
    -0.63
     eventualmente
    -0.57
    DataAnnotations
    -0.53
    __':
    -0.50
     thither
    -0.49
     genomen
    -0.49
     frère
    -0.48
    Folgende
    -0.47
    THIS
    -0.47
    føl
    -0.47
    POSITIVE LOGITS
     للاسماء
    0.87
    XmlEnum
    0.71
    InjectAttribute
    0.68
    webElementXpaths
    0.65
    ‗
    0.64
     createSprite
    0.63
    windowFixed
    0.61
    AccessorTable
    0.60
    fromCharCode
    0.60
    chèque
    0.59
    Activations Density 1.271%

    No Known Activations