© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3562
    Prev
    Next
    INDEX
    Explanations

    mentions of bikes alone, or general statements

    oai_token-act-pair · gemini-2.0-flash

    bike

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    RegressionTest
    -0.64
    PropertyGroup
    -0.62
    /*---
    -0.59
    gefunden
    -0.57
    mobileqq
    -0.56
     propOrder
    -0.56
    VideoCapture
    -0.55
    ObjectContext
    -0.54
    DOCTYPE
    -0.52
    bní
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.77
    er
    0.69
     ILogger
    0.66
     CHtml
    0.66
     دیکھیے
    0.66
     Schweitzer
    0.63
     Gier
    0.62
    able
    0.59
    NamedQueries
    0.59
     تضيفلها
    0.58
    Activations Density 1.247%

    No Known Activations