© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13885
    Prev
    Next
    INDEX
    Explanations

    C++ code, conditional statements, and comparisons

    oai_token-act-pair · gemini-2.0-flash

    code, configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ()}}
    -0.53
     Instantly
    -0.53
    Neigh
    -0.50
    corrhi
    -0.50
     Waray
    -0.49
     تانيه
    -0.48
     peine
    -0.48
    olyb
    -0.47
     PropertyChanged
    -0.47
     bolí
    -0.46
    POSITIVE LOGITS
    bewerken
    0.89
    UnusedPrivate
    0.66
     AssemblyProduct
    0.64
    GEBURTSDATUM
    0.57
    initComponents
    0.56
    ControllerAdvice
    0.52
     newBuilder
    0.52
     Broughton
    0.52
    تقاوى
    0.51
    ientes
    0.50
    Activations Density 2.979%

    No Known Activations