© 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. 15381
    Prev
    Next
    INDEX
    Explanations

    words related to artistic endeavors like galleries, artists, artworks, and authors

    oai_token-act-pair · gemini-2.0-flash

    work

    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
     dispozici
    -0.51
    패
    -0.48
    Спасылкі
    -0.46
    inazione
    -0.45
    Tikang
    -0.45
    komsten
    -0.44
    BindView
    -0.44
     eikä
    -0.42
     oignons
    -0.42
     linkovi
    -0.41
    POSITIVE LOGITS
     work
    3.03
    work
    2.61
     works
    2.52
    Work
    2.34
     Work
    2.30
     WORK
    2.17
    works
    2.13
    WORK
    2.03
     Works
    1.98
    Works
    1.96
    Activations Density 4.995%

    No Known Activations