© 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. 12169
    Prev
    Next
    INDEX
    Explanations

    the word "way", "pace", "track", "Friday", or "website"

    oai_token-act-pair · gemini-2.0-flash

    movement or progress

    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
    :✨
    -0.94
    <bos>
    -0.94
    NameInMap
    -0.90
    queryInterface
    -0.84
     rhestr
    -0.84
     تانيه
    -0.75
     initComponents
    -0.73
     كورة
    -0.73
    __':
    -0.72
    URLException
    -0.71
    POSITIVE LOGITS
     to
    0.58
     Urbana
    0.53
    Welcome
    0.50
     Welcome
    0.49
    welcome
    0.48
     bienven
    0.48
    er
    0.48
    WindowConstants
    0.47
     welcome
    0.47
     leveling
    0.47
    Activations Density 0.522%

    No Known Activations