© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2818
    Prev
    Next
    INDEX
    Explanations

    words related to computers, networks, and software, especially related to things currently happening

    oai_token-act-pair · gemini-2.0-flash

    running

    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
     running
    -1.48
    Running
    -1.30
    running
    -1.29
     Running
    -1.27
     RUNNING
    -1.17
     standing
    -1.05
    RUNNING
    -1.05
     walking
    -0.95
    <bos>
    -0.93
     sitting
    -0.93
    POSITIVE LOGITS
     Run
    0.56
     run
    0.56
    Run
    0.55
    run
    0.55
     (;;
    0.54
    marry
    0.54
     Polity
    0.52
    adaptiveStyles
    0.50
    beln
    0.49
     skew
    0.48
    Activations Density 15.423%

    No Known Activations