© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11503
    Prev
    Next
    INDEX
    Explanations

    financial costs and numbers, often with the words "about" or "over"

    oai_token-act-pair · gemini-2.0-flash

    monetary amounts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     tip
    -0.97
    tip
    -0.88
     Tip
    -0.87
     tips
    -0.80
    Tip
    -0.79
     Tips
    -0.76
     tipped
    -0.75
     TIP
    -0.75
    tipped
    -0.74
    Tips
    -0.73
    POSITIVE LOGITS
    Autoritní
    0.88
    rrggbb
    0.85
    webElementXpaths
    0.82
    MigrationBuilder
    0.82
     utafitiHapana
    0.80
     препратки
    0.73
    Vidite
    0.71
    :✨
    0.71
    keyColumn
    0.71
    HomeAsUpEnabled
    0.70
    Activations Density 2.445%

    No Known Activations