© 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. 11837
    Prev
    Next
    INDEX
    Explanations

    words associated with entertainment and media consumption, especially in the context of audiences.

    oai_token-act-pair · gemini-2.0-flash

    Media consumers

    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
     audience
    -0.77
     Theſe
    -0.74
    :+:
    -0.71
     audiences
    -0.70
    Audiences
    -0.68
     consumers
    -0.65
     fans
    -0.65
     itſelf
    -0.65
    读者
    -0.64
     Italijani
    -0.64
    POSITIVE LOGITS
    loroethene
    0.52
    pexpr
    0.49
    日閲覧
    0.49
    Meds
    0.48
     kick
    0.46
     VIDEOTAPE
    0.44
    kick
    0.44
     Bhd
    0.44
     dock
    0.43
    Scripts
    0.43
    Activations Density 16.144%

    No Known Activations