© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5481
    Prev
    Next
    INDEX
    Explanations

    mentions of physical parts or components of something, whether it be physical, textual, or medical.

    oai_token-act-pair · gemini-2.0-flash

    sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     sections
    -1.36
     batches
    -1.33
     categories
    -1.29
     phases
    -1.27
     segments
    -1.26
     chapters
    -1.24
    Sections
    -1.23
     Sections
    -1.19
    sections
    -1.17
     groups
    -1.16
    POSITIVE LOGITS
     group
    0.73
     section
    0.66
     lot
    0.66
     class
    0.64
     box
    0.64
    verwijspagina
    0.61
     unit
    0.61
     panel
    0.59
     band
    0.58
    ilton
    0.57
    Activations Density 5.740%

    No Known Activations