© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4398
    Prev
    Next
    INDEX
    Explanations

    words that are connected to relationships, devices, publications, and clinical trials.

    oai_token-act-pair · gemini-2.0-flash

    Details about entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    NameInMap
    -0.61
     للاسماء
    -0.60
    IntoConstraints
    -0.59
     []);
    -0.57
    TestingModule
    -0.56
     estekak
    -0.56
     Wikimedijinoj
    -0.56
     scom
    -0.56
    usermodel
    -0.54
    )++;
    -0.54
    POSITIVE LOGITS
    ----</
    0.56
    ónimos
    0.47
    trons
    0.47
    splat
    0.46
    abestanden
    0.46
     AssemblyProduct
    0.44
    }{*}{}
    0.44
    webElementXpaths
    0.44
    pezi
    0.44
    edance
    0.43
    Activations Density 9.150%

    No Known Activations