© 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. 9438
    Prev
    Next
    INDEX
    Explanations

    titles of scientific publications or books

    oai_token-act-pair · gemini-2.0-flash

    elementary theory

    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
     initComponents
    -0.65
    setminus
    -0.56
    jScrollPane
    -0.54
    schild
    -0.53
    '},
    -0.49
     Chemie
    -0.47
    %;
    -0.47
    orphism
    -0.47
     техника
    -0.47
     لیے
    -0.46
    POSITIVE LOGITS
    IUrlHelper
    0.81
     AssemblyCulture
    0.65
    NameInMap
    0.63
     Савезне
    0.57
     Италијани
    0.57
     cherchés
    0.56
    InstrumentedTest
    0.54
    PyExc
    0.53
     Italijanski
    0.52
     disambiguazione
    0.51
    Activations Density 0.648%

    No Known Activations