© 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. 11975
    Prev
    Next
    INDEX
    Explanations

    floating point numbers and code snippets

    oai_token-act-pair · gemini-2.0-flash

    usage of certain data structures in code

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

    0

    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
     препратки
    -0.84
     مشين
    -0.75
    mybatisplus
    -0.70
    Portale
    -0.67
    IGraphics
    -0.67
     الرياضيه
    -0.64
    abestanden
    -0.63
    RectangleBorder
    -0.62
    webElementXpaths
    -0.61
    rrggbb
    -0.61
    POSITIVE LOGITS
    use
    0.45
     ouv
    0.42
     use
    0.42
     estrenar
    0.42
    jsonPath
    0.40
     coppia
    0.40
     række
    0.40
     použ
    0.40
     Auseinander
    0.39
     стъ
    0.39
    Activations Density 2.512%

    No Known Activations