© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10192
    Prev
    Next
    INDEX
    Explanations

    terms related to air travel

    oai_token-act-pair · gemini-2.0-flash

    airlines and airports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     BoxFit
    -0.79
    IsContent
    -0.62
    Personensuche
    -0.60
    mybatisplus
    -0.59
    ArrowToggle
    -0.57
    ISupport
    -0.57
     getClient
    -0.57
     Walkover
    -0.57
    ++]=
    -0.56
    uesia
    -0.56
    POSITIVE LOGITS
     Airways
    0.49
     tangga
    0.47
    >?
    0.47
    Own
    0.46
    hela
    0.44
    SuppressMessage
    0.43
     ticketing
    0.41
    Personendaten
    0.41
    handling
    0.41
    PLS
    0.40
    Activations Density 0.290%

    No Known Activations