© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11284
    Prev
    Next
    INDEX
    Explanations

    non-English words, numbers alone, and words related to legal proceedings or finance in English

    oai_token-act-pair · gemini-2.0-flash

    mixed technical content

    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
    homonymie
    -0.62
    reportWebVitals
    -0.56
    ArrowToggle
    -0.56
     d
    -0.54
    Enllaces
    -0.50
    LLocation
    -0.49
    himovic
    -0.49
    awtextra
    -0.49
    esez
    -0.48
    routeProvider
    -0.48
    POSITIVE LOGITS
    ftagPool
    0.55
     Crot
    0.53
     pinch
    0.51
     समीक्षाओं
    0.50
     Digit
    0.50
     stalk
    0.50
    tart
    0.50
     sute
    0.49
     DIGIT
    0.49
     pinching
    0.49
    Activations Density 1.603%

    No Known Activations