© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 68
    Prev
    Next
    INDEX
    Explanations

    seemingly random but perhaps finds numbers, and location/naming of academic writing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     propOrder
    -1.16
    SourceChecksum
    -1.15
    InjectAttribute
    -1.15
    تقاوى
    -1.13
    contentLoaded
    -1.11
    principalTable
    -1.10
    DockStyle
    -1.07
    ArrowToggle
    -1.03
     незавершена
    -1.02
    ValueStyle
    -1.02
    POSITIVE LOGITS
     ha
    0.48
    ..
    0.47
     une
    0.47
     (
    0.45
     min
    0.44
     Clearly
    0.44
     cont
    0.44
     un
    0.43
     selv
    0.43
     gre
    0.42
    Activations Density 14.748%

    No Known Activations