© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15130
    Prev
    Next
    INDEX
    Explanations

    the word 'run', often with the word 'out'.

    oai_token-act-pair · gemini-2.0-flash

    running out

    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
     run
    -1.05
     Run
    -1.01
    Run
    -0.99
     ran
    -0.96
     Running
    -0.93
    run
    -0.92
     running
    -0.92
    Running
    -0.92
     RUN
    -0.91
     runs
    -0.87
    POSITIVE LOGITS
    MemoryWarning
    0.68
    InitVars
    0.62
     الاطلاع
    0.59
     الدولى
    0.57
     disambiguazione
    0.54
    extAlignment
    0.54
    antMatchers
    0.53
     Âge
    0.52
    DECREF
    0.52
    ंदीखरीदारी
    0.52
    Activations Density 0.602%

    No Known Activations