© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14293
    Prev
    Next
    INDEX
    Explanations

    code referring to objects, particularly JSON objects, and their types in a programming language like Java or Objective-C

    oai_token-act-pair · gemini-2.0-flash

    obj

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AssemblyVersion
    -0.90
    RegressionTest
    -0.85
     ब्रेकडाउन
    -0.84
    Lähteet
    -0.81
     mostrarán
    -0.78
    はじめに
    -0.78
     Wikiseite
    -0.68
    EndProject
    -0.68
     muualla
    -0.68
     Vikipedi
    -0.68
    POSITIVE LOGITS
     EXISTS
    0.51
    “
    0.50
    The
    0.49
     mukaan
    0.48
    eful
    0.47
    Тарихы
    0.47
     kasarigan
    0.46
    key
    0.46
     électriques
    0.45
    ceğiniz
    0.44
    Activations Density 0.652%

    No Known Activations