© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10344
    Prev
    Next
    INDEX
    Explanations

    words associated with company culture, values, and mission

    oai_token-act-pair · gemini-2.0-flash

    terms related to organizational missions and values

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

    Mission and values

    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
     <>",
    -0.61
    elemField
    -0.60
    sizeCache
    -0.58
    UnusedPrivate
    -0.57
    SuspendLayout
    -0.54
     unknownFields
    -0.52
    :✨
    -0.51
    Espèce
    -0.50
    WebServlet
    -0.48
    ImageContext
    -0.47
    POSITIVE LOGITS
     mission
    1.78
    mission
    1.55
     Mission
    1.47
     values
    1.44
     MISSION
    1.40
     missions
    1.40
    Mission
    1.37
     misión
    1.27
     Values
    1.27
     objectives
    1.27
    Activations Density 2.656%

    No Known Activations