© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3282
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases relating to nature

    oai_token-act-pair · gemini-2.0-flash

    air

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AccessorTable
    -0.63
    help
    -0.56
     help
    -0.56
    AsUp
    -0.56
     ویکی‌پدیا
    -0.50
     Help
    -0.50
    
    -0.49
    labor
    -0.48
     geslacht
    -0.47
     beginnetje
    -0.47
    POSITIVE LOGITS
     air
    1.95
    air
    1.45
    Air
    1.41
     Air
    1.38
     AIR
    1.27
     lucht
    1.22
     airs
    1.16
    AIR
    1.14
     luft
    1.06
     Luft
    1.05
    Activations Density 2.388%

    No Known Activations