© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14321
    Prev
    Next
    INDEX
    Explanations

    words associated with coatings and metal finishing

    oai_token-act-pair · gemini-2.0-flash

    plated or chrome

    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
    StoryboardSegue
    -1.02
    setVerticalGroup
    -0.97
     Efq
    -0.84
    RenderAtEndOf
    -0.83
    Personendaten
    -0.81
    richTextPanel
    -0.80
     ObjectParameter
    -0.80
    WebVitals
    -0.79
    parsedMessage
    -0.77
    ValueStyle
    -0.77
    POSITIVE LOGITS
    mod
    0.47
     
    0.46
     mod
    0.46
    <eos>
    0.45
    fortawesome
    0.45
     “
    0.45
     Mar
    0.43
     "
    0.42
     mar
    0.42
     sa
    0.42
    Activations Density 0.635%

    No Known Activations