© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13609
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to planning and design.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     LUMP
    -0.59
     occurrences
    -0.58
     Ceres
    -0.57
     Bary
    -0.57
     ◄
    -0.56
    igslist
    -0.55
    ℉
    -0.55
    ील
    -0.55
    ädie
    -0.54
     fileList
    -0.54
    POSITIVE LOGITS
     diseñ
    0.82
     design
    0.74
    designed
    0.72
     designed
    0.71
     diseño
    0.70
     diseños
    0.64
    Designing
    0.64
     designing
    0.64
     desain
    0.62
    design
    0.61
    Activations Density 2.660%

    No Known Activations