© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6346
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns

    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
     by
    -2.17
    by
    -1.59
     oleh
    -1.54
     By
    -1.42
    By
    -1.37
     توسط
    -1.27
     BY
    -1.21
     ידי
    -1.15
    ById
    -0.99
     przez
    -0.94
    POSITIVE LOGITS
     Chwiliwch
    0.72
     kanssa
    0.64
     ProtoMessage
    0.62
    IntoConstraints
    0.58
    zugehen
    0.57
     استنادى
    0.57
     initComponents
    0.57
    ymce
    0.56
    ScopeManager
    0.55
    SourceChecksum
    0.55
    Activations Density 1.541%

    No Known Activations