© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11366
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating some form of change or conversion

    oai_token-act-pair · gemini-2.0-flash

    Scientific descriptions/classifications

    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
    AddTagHelper
    -0.85
    awtextra
    -0.75
    CppCodeGen
    -0.74
     "..\..\..\
    -0.73
    Билгалдахарш
    -0.69
    bootstrapcdn
    -0.69
    
    -0.68
    ViewImports
    -0.66
     يتيمه
    -0.65
     "..\..\
    -0.63
    POSITIVE LOGITS
     चाहते
    0.51
    存于互联网档案馆
    0.50
     دیکھیے
    0.47
    endregion
    0.45
    inheritDoc
    0.42
    exitRule
    0.42
    hetically
    0.42
    dellín
    0.40
    BoxLayout
    0.40
    chließend
    0.39
    Activations Density 2.057%

    No Known Activations