© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13848
    Prev
    Next
    INDEX
    Explanations

    text related to scientific publications, especially ethics and declarations of competing interests.

    oai_token-act-pair · gemini-2.0-flash

    academic research papers

    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
    <bos>
    -0.78
    oredCriteria
    -0.77
     '\\;'
    -0.73
    Хьажоргаш
    -0.69
    sizeCache
    -0.67
    횟
    -0.67
    RegressionTest
    -0.65
    Diweddarwch
    -0.64
    GEBURTSDATUM
    -0.62
    ględ
    -0.59
    POSITIVE LOGITS
     Scritto
    0.62
    MemoryWarning
    0.60
     Audiodateien
    0.58
    Hochspringen
    0.56
    httphttps
    0.55
     elseif
    0.54
    BeginInit
    0.54
    prepareStatement
    0.52
     فريبيس
    0.52
     BoxDecoration
    0.50
    Activations Density 1.482%

    No Known Activations