© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4757
    Prev
    Next
    INDEX
    Explanations

    dates and names of people and organizations, suggesting it focuses on historical events or timelines

    oai_token-act-pair · gemini-2.0-flash

    purchase/ownership

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    SharedCtor
    -0.79
     betweenstory
    -0.63
    पया
    -0.58
    Personensuche
    -0.57
    verwijspagina
    -0.52
    ыгана
    -0.52
    Personendaten
    -0.52
     Мексичка
    -0.51
     odkazy
    -0.50
     transférez
    -0.50
    POSITIVE LOGITS
     purchase
    0.67
    EndGlobalSection
    0.62
     purchased
    0.61
     contracted
    0.59
     ownership
    0.58
    purchase
    0.57
     borrow
    0.55
    purchased
    0.54
     owns
    0.53
    Scénario
    0.53
    Activations Density 4.553%

    No Known Activations