© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10964
    Prev
    Next
    INDEX
    Explanations

    words or abbreviations used in code and computing

    oai_token-act-pair · gemini-2.0-flash

    Technology/Programming

    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
     Xuân
    -0.52
    蓄
    -0.51
    stahl
    -0.51
    makeText
    -0.48
     trái
    -0.48
     either
    -0.47
     lawan
    -0.47
     subida
    -0.47
     woj
    -0.47
     ex
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.89
     '\\;'
    0.84
     betweenstory
    0.77
     дописавши
    0.76
     mergeFrom
    0.71
     Italijanski
    0.69
    HtmlAttribute
    0.69
    chables
    0.67
    enderror
    0.66
    OGND
    0.66
    Activations Density 2.559%

    No Known Activations