© 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. 656
    Prev
    Next
    INDEX
    Explanations

    words related to inventions, amusement park rides, and playgrounds

    oai_token-act-pair · gemini-2.0-flash

    Ferris wheel and monkey bars

    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
     HasFactory
    -0.80
     nahilalakip
    -0.77
    findpost
    -0.76
    حياته
    -0.67
    HostException
    -0.65
     InputDecoration
    -0.65
    BeginContext
    -0.64
     lakh
    -0.62
    TagMode
    -0.62
     Beatrix
    -0.61
    POSITIVE LOGITS
     hanging
    0.48
     gantung
    0.47
    hanging
    0.45
     trellis
    0.44
    ofollow
    0.44
     hung
    0.43
     häng
    0.43
    Билгалдахарш
    0.40
     Spannung
    0.40
    Hanging
    0.40
    Activations Density 1.124%

    No Known Activations