© 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. 10247
    Prev
    Next
    INDEX
    Explanations

    words indicating that time is being allocated to something

    oai_token-act-pair · gemini-2.0-flash

    research and analysis

    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
     régulier
    -0.45
     hendes
    -0.45
     medlems
    -0.43
     celulares
    -0.42
    oxide
    -0.42
    EROUS
    -0.42
    owników
    -0.41
     cellulare
    -0.41
     enged
    -0.40
     cser
    -0.40
    POSITIVE LOGITS
     تضيفلها
    0.73
    <bos>
    0.68
    íncia
    0.68
    Panamoan
    0.67
    writeFieldEnd
    0.67
    RRect
    0.65
    DrawerToggle
    0.64
    acabana
    0.61
    enderror
    0.60
    dafx
    0.60
    Activations Density 1.904%

    No Known Activations