© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14029
    Prev
    Next
    INDEX
    Explanations

    terms related to programming, specifically those associated with logging and running code

    oai_token-act-pair · gemini-2.0-flash

    log

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     log
    -2.41
    log
    -2.36
    Log
    -2.17
     Log
    -2.09
    LOG
    -1.92
     LOG
    -1.82
     logs
    -1.74
     Logs
    -1.52
    logs
    -1.51
    Logs
    -1.45
    POSITIVE LOGITS
    RegistryLite
    0.85
     Normdatei
    0.82
     متعلقه
    0.81
    IonicModule
    0.80
    bootstrapcdn
    0.76
     Italijanski
    0.73
    anskje
    0.73
     تانيه
    0.71
    NameInMap
    0.70
    OrBuilder
    0.69
    Activations Density 4.613%

    No Known Activations