© 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. 12564
    Prev
    Next
    INDEX
    Explanations

    code syntax, specifically C++ and C#

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax and keywords

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

    Code snippets

    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
    //</
    -0.62
     ویکی‌پدی
    -0.60
     nakalista
    -0.57
    الإنجليزية
    -0.54
    GraphicsUnit
    -0.53
    dal
    -0.52
    ja
    -0.51
    rew
    -0.50
    dir
    -0.50
    ink
    -0.50
    POSITIVE LOGITS
    didSet
    0.48
    SharedCtor
    0.47
     kasarigan
    0.46
    ContentAsync
    0.46
    ")));
    0.43
    cstdio
    0.41
    ennifer
    0.40
    _;
    0.39
    oredCriteria
    0.37
    Содержание
    0.37
    Activations Density 1.545%

    No Known Activations