© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2342
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions of experimental data in scientific papers.

    oai_token-act-pair · gemini-2.0-flash

    experimental

    np_max-act · 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
     посо
    -0.48
    ueira
    -0.47
    bok
    -0.45
     Rem
    -0.44
     osp
    -0.43
    Maps
    -0.43
     its
    -0.43
    fortawesome
    -0.43
    őd
    -0.42
     Yates
    -0.42
    POSITIVE LOGITS
    \{\\
    0.73
     Waray
    0.71
    ParallelGroup
    0.67
      (
    0.66
     nakalista
    0.64
    LayoutConstraint
    0.63
    ExtendWith
    0.61
    abetes
    0.59
     sceptre
    0.58
     AssemblyCompany
    0.58
    Activations Density 9.201%

    No Known Activations