© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15113
    Prev
    Next
    INDEX
    Explanations

    words associated with being at a restaurant or similar establishment

    oai_token-act-pair · gemini-2.0-flash

    Furniture

    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
     side
    -0.53
    pogon
    -0.45
     Valdez
    -0.44
    HRESULT
    -0.44
    typeorm
    -0.43
     coli
    -0.43
    InteropServices
    -0.42
     lái
    -0.42
    ötet
    -0.42
     AttributeSet
    -0.42
    POSITIVE LOGITS
    DockStyle
    0.74
    RegistryLite
    0.69
     betweenstory
    0.63
     للمعارف
    0.63
    ItemBackground
    0.63
    IUrlHelper
    0.63
    ніципалі
    0.61
    versible
    0.61
    RegressionTest
    0.60
     kasarigan
    0.59
    Activations Density 3.891%

    No Known Activations