© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13942
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with products and manufacturing, often in the context of describing features, flaws, or technical specifications

    oai_token-act-pair · gemini-2.0-flash

    Car maintenance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     linkovi
    -0.63
    UrlResolution
    -0.54
    LookAnd
    -0.54
    Corollary
    -0.52
     INTERESAR
    -0.50
    
    -0.50
     متعلقه
    -0.47
    KERN
    -0.47
    ніципа
    -0.46
     ProtoMessage
    -0.46
    POSITIVE LOGITS
     postIndex
    0.56
    Marketplace
    0.51
    roek
    0.50
     Majesté
    0.50
    argest
    0.50
    racuse
    0.50
     Majefty
    0.50
     تضيفلها
    0.49
    padre
    0.49
     Komponist
    0.49
    Activations Density 1.606%

    No Known Activations