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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6607
    Prev
    Next
    INDEX
    Explanations

    text discussing business, planning and physical resources

    oai_token-act-pair · gemini-2.0-flash

    words related to aviation and airport operations

    np_token-act-pair-logits · gpt-4o-mini

    runways and approaches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SourceChecksum
    -0.60
    AddHtmlAttribute
    -0.54
    RTLD
    -0.53
     المعيارى
    -0.51
    adaptiveStyles
    -0.50
     كومونز
    -0.50
    AsUp
    -0.50
    клопе
    -0.48
    /**
    -0.48
    alyptus
    -0.47
    POSITIVE LOGITS
     Approach
    0.75
     runway
    0.72
     Runway
    0.71
     approach
    0.71
    run
    0.70
    Approach
    0.68
    approach
    0.68
    Run
    0.68
     APPROACH
    0.65
     runways
    0.64
    Activations Density 0.627%

    No Known Activations