© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5467
    Prev
    Next
    INDEX
    Explanations

    code-related terms like "add", "main", "window," "layer", and code punctuation like "->"

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords and functions

    np_token-act-pair-logits · gpt-4o-mini

    GUI and software development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    addCriterion
    -0.62
    UrlResolution
    -0.62
    thâu
    -0.60
    BeginContext
    -0.59
    MessageTagHelper
    -0.55
     esterni
    -0.50
     CreateTagHelper
    -0.50
    FieldNumber
    -0.50
     âges
    -0.49
     الدولى
    -0.48
    POSITIVE LOGITS
     EconPapers
    0.60
    XmlEnum
    0.57
    ugno
    0.57
     חיצוניים
    0.57
     window
    0.52
    Hozzáférés
    0.51
     selection
    0.50
     الاطلاع
    0.50
     calendriers
    0.49
    setCursor
    0.48
    Activations Density 12.968%

    No Known Activations