© 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. 3568
    Prev
    Next
    INDEX
    Explanations

    mentions of gears and gear-making

    oai_token-act-pair · gemini-2.0-flash

    gear

    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
    hdashline
    -0.68
    "';
    -0.66
    "){
    -0.63
    ?..
    -0.61
     CGFloat
    -0.60
    '...
    -0.60
     ="";
    -0.60
    amssymb
    -0.60
    '){
    -0.60
     ieder
    -0.60
    POSITIVE LOGITS
    Geplaatst
    0.79
    UnsafeEnabled
    0.74
    WithIOException
    0.71
     FishBase
    0.67
    complexContent
    0.66
    featureID
    0.66
    Personendaten
    0.66
     kasarigan
    0.66
    LayoutStyle
    0.64
    IndentedString
    0.64
    Activations Density 1.439%

    No Known Activations