© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12388
    Prev
    Next
    INDEX
    Explanations

    past-tense forms of the verb "to be" and language around securing/trailing in sports matches

    oai_token-act-pair · gemini-2.0-flash

    Sports news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     propOrder
    -0.60
     zasi
    -0.57
     opérés
    -0.55
    omás
    -0.55
    CopyWith
    -0.55
    PMailer
    -0.54
     cherchés
    -0.52
    awtextra
    -0.52
     bağlantılar
    -0.51
    DrawerToggle
    -0.51
    POSITIVE LOGITS
     jScrollPane
    0.52
     supervivencia
    0.49
     survival
    0.48
     AssemblyProduct
    0.46
     relâche
    0.44
    pys
    0.44
     geophysical
    0.44
    mäßigen
    0.44
     NUKAT
    0.43
     tecnici
    0.43
    Activations Density 0.897%

    No Known Activations