© 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. 7402
    Prev
    Next
    INDEX
    Explanations

    content related to music such as albums, bands, and songs

    oai_token-act-pair · gemini-2.0-flash

    terms related to live performances or recordings

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

    live or covers

    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
     nahilalakip
    -0.81
    queryInterface
    -0.75
    setVerticalGroup
    -0.69
     transférez
    -0.68
    GEBURTSDATUM
    -0.68
    basicConfig
    -0.67
    RenderAtEndOf
    -0.65
     music
    -0.64
     EconPapers
    -0.63
    MessageOf
    -0.63
    POSITIVE LOGITS
     live
    1.18
    live
    0.99
    Live
    0.93
     Live
    0.93
     LIVE
    0.85
    LIVE
    0.78
     canlı
    0.62
     cover
    0.58
     زنده
    0.57
     covers
    0.57
    Activations Density 0.900%

    No Known Activations