© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7452
    Prev
    Next
    INDEX
    Explanations

    second-person pronouns used in the context of buying, selling, or lending

    oai_token-act-pair · gemini-2.0-flash

    purchases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    auro
    -0.56
    rieb
    -0.50
    kün
    -0.50
     pochod
    -0.49
    Display
    -0.49
     Vikipedi
    -0.49
     समीक्षाओं
    -0.48
    INTS
    -0.46
     emerge
    -0.46
     defending
    -0.46
    POSITIVE LOGITS
     purchased
    1.02
     bought
    0.86
     purchase
    0.85
    InjectAttribute
    0.78
     purchases
    0.77
     Purchased
    0.77
    purchased
    0.76
    bollah
    0.75
     elected
    0.73
     purchasing
    0.73
    Activations Density 4.279%

    No Known Activations