© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9583
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to programming code and compiler behavior, particularly concerning method overloading, exceptions, and APIs.

    oai_token-act-pair · gemini-2.0-flash

    Overloads and signatures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     createState
    -0.54
     }}">
    -0.46
     препратки
    -0.45
    EndInit
    -0.42
    Transkript
    -0.42
    swig
    -0.42
    Circa
    -0.42
     진
    -0.40
     courant
    -0.40
    INSTALLED
    -0.40
    POSITIVE LOGITS
    ValueStyle
    0.78
    contentLoaded
    0.76
     AssemblyCulture
    0.68
    Demografie
    0.66
     ostavi
    0.64
     rospy
    0.62
     protoimpl
    0.61
     relâche
    0.61
    SequentialGroup
    0.60
     colectiva
    0.60
    Activations Density 1.321%

    No Known Activations