© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10542
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas containing the word "log"

    oai_token-act-pair · gemini-2.0-flash

    logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -2.61
     Log
    -2.58
    Log
    -2.39
    log
    -2.39
     LOG
    -2.36
     logs
    -2.28
    LOG
    -2.27
     Logs
    -2.17
     logging
    -2.16
    logs
    -2.11
    POSITIVE LOGITS
    úgó
    0.58
    GraphicsUnit
    0.57
     Houſe
    0.56
     CWE
    0.54
    upol
    0.53
    ншни
    0.53
     Harriet
    0.53
     Bress
    0.53
     preſent
    0.52
    phens
    0.52
    Activations Density 1.548%

    No Known Activations