© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8828
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to tourist activities and city guides

    oai_token-act-pair · gemini-2.0-flash

    tourist attractions

    np_token-act-pair-logits · gpt-4o-mini

    places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    transQ
    -0.65
    SpringBootTest
    -0.62
    Havolalar
    -0.59
    GOTREF
    -0.57
     AssemblyCompany
    -0.55
    SuppressMessage
    -0.55
     MURRAY
    -0.52
    Personendaten
    -0.50
     Мексичка
    -0.49
    makeConstraints
    -0.48
    POSITIVE LOGITS
     spots
    0.69
     lieux
    0.59
     Spots
    0.59
     places
    0.59
     landmarks
    0.58
     hotspots
    0.58
    Lugar
    0.57
     LIABLE
    0.56
     place
    0.55
     UNESCO
    0.55
    Activations Density 4.260%

    No Known Activations