© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12256
    Prev
    Next
    INDEX
    Explanations

    scientific or medical studies or research being performed or conducted

    oai_token-act-pair · gemini-2.0-flash

    conducted/performed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     performed
    -1.37
     conducted
    -1.31
     Performed
    -1.25
    performed
    -1.11
    conducted
    -1.10
     Conducted
    -1.05
     carried
    -0.90
    Performed
    -0.90
     uitgevoerd
    -0.90
     undertaken
    -0.85
    POSITIVE LOGITS
     kaynağından
    0.59
     play
    0.59
    :✨
    0.53
    DataBinding
    0.49
     use
    0.48
    rlpool
    0.48
    play
    0.48
     feed
    0.48
    omencl
    0.48
    CreateModel
    0.47
    Activations Density 1.709%

    No Known Activations