© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3875
    Prev
    Next
    INDEX
    Explanations

    references to mass media including news, events, broadcasting, entertainment industry, television and movies

    oai_token-act-pair · gemini-2.0-flash

    audiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    XmlAccessType
    -0.61
    ArgsConstructor
    -0.53
    BeginContext
    -0.51
     Baillargeon
    -0.44
    ActionCreators
    -0.43
    ysacchar
    -0.43
     ***!
    -0.41
    urtstag
    -0.39
    ComponentModel
    -0.38
    bua
    -0.38
    POSITIVE LOGITS
     audiences
    2.03
     viewers
    2.03
     audience
    1.94
     listeners
    1.88
     fans
    1.84
     readers
    1.83
     consumers
    1.81
     voters
    1.69
     users
    1.66
     customers
    1.66
    Activations Density 8.443%

    No Known Activations