© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15731
    Prev
    Next
    INDEX
    Explanations

    descriptions of components, especially in a mechanical context, often involving directional or connective terms

    oai_token-act-pair · gemini-2.0-flash

    wheels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    obiety
    -0.60
     man
    -0.60
    woman
    -0.59
     hombre
    -0.59
    ennia
    -0.58
     homme
    -0.57
    uomo
    -0.56
    man
    -0.56
     تضيفلها
    -0.56
    homme
    -0.54
    POSITIVE LOGITS
     wheels
    0.91
     Wheels
    0.82
    IntoConstraints
    0.80
    Wheels
    0.75
     tracks
    0.74
     WHE
    0.74
     rollers
    0.72
     casters
    0.71
    wheels
    0.68
     rolling
    0.67
    Activations Density 0.753%

    No Known Activations