© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1849
    Prev
    Next
    INDEX
    Explanations

    words related to gamification, personal connection, or what makes us human

    oai_token-act-pair · gemini-2.0-flash

    gamification and design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     GenerationType
    -0.82
    исленность
    -0.75
    IUrlHelper
    -0.73
     виправивши
    -0.68
     تضيفلها
    -0.68
    AutoScaleMode
    -0.67
    TagMode
    -0.67
    WireFormatLite
    -0.66
    WithIOException
    -0.65
    ]--;
    -0.63
    POSITIVE LOGITS
     personal
    0.71
     Personal
    0.64
     PERSONAL
    0.61
    PERSONAL
    0.60
    Personal
    0.58
    parsedMessage
    0.56
     persönlichen
    0.55
    <bos>
    0.54
    personal
    0.53
     persoonlijke
    0.50
    Activations Density 1.533%

    No Known Activations