© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12627
    Prev
    Next
    INDEX
    Explanations

    scientific text related to electromagnetism, dielectrics, and materials science, possibly including equations, symbols, and references

    oai_token-act-pair · gemini-2.0-flash

    Physics and materials science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    tvguidetime
    -0.98
    fromnode
    -0.61
    richTextPanel
    -0.57
    Rhestr
    -0.55
    complexContent
    -0.55
    AccessorTable
    -0.54
    EndContext
    -0.54
    sizeCache
    -0.53
    colgroup
    -0.52
    hlands
    -0.52
    POSITIVE LOGITS
     sp
    0.44
    IsMutable
    0.44
     discorso
    0.44
     deuter
    0.44
     erw
    0.43
    gy
    0.43
    iastical
    0.43
     xenon
    0.43
    dyna
    0.43
    eschou
    0.42
    Activations Density 12.059%

    No Known Activations