© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11277
    Prev
    Next
    INDEX
    Explanations

    verbs related to changing state or moving

    oai_token-act-pair · gemini-2.0-flash

    general motion

    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
     kasarigan
    -0.86
    Personensuche
    -0.84
    المناصب
    -0.77
    InjectAttribute
    -0.70
    :✨
    -0.69
    /*---
    -0.68
    RegistryLite
    -0.68
    writeField
    -0.66
    CloseOperation
    -0.65
    ↷
    -0.65
    POSITIVE LOGITS
     standing
    0.89
     walking
    0.80
    Standing
    0.75
     jumping
    0.71
     running
    0.69
    Walking
    0.69
     sitting
    0.68
     Walking
    0.67
     Standing
    0.67
     driving
    0.66
    Activations Density 2.281%

    No Known Activations