© 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. 13949
    Prev
    Next
    INDEX
    Explanations

    suffixes such as "-ical", "-al", and "-ly" attached to words, along with the letters "l" and "y."

    oai_token-act-pair · gemini-2.0-flash

    Code or technical language

    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
     okuyayım
    -0.57
    ri
    -0.46
    Miri
    -0.45
    transQ
    -0.44
    Experience
    -0.44
     논
    -0.43
    Mir
    -0.43
     useParams
    -0.43
    Facades
    -0.42
    ATTR
    -0.41
    POSITIVE LOGITS
     ExecuteAsync
    0.78
    MLLoader
    0.72
    yy
    0.70
    ,‎
    0.68
     Iy
    0.68
    ryt
    0.68
    ayy
    0.66
    EndGlobalSection
    0.65
    ây
    0.64
    uy
    0.64
    Activations Density 1.085%

    No Known Activations