© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6610
    Prev
    Next
    INDEX
    Explanations

    the string "utf-8" and related terms like "unicode," as commonly associated with character encoding

    oai_token-act-pair · gemini-2.0-flash

    words and phrases related to UTF encodings

    np_token-act-pair-logits · gpt-4o-mini

    utf

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Referències
    -0.68
     nakalista
    -0.64
    AddHtmlAttribute
    -0.63
    InputTagHelper
    -0.60
     مشين
    -0.59
     estimés
    -0.59
    tonsoft
    -0.57
    transQ
    -0.57
     BrowserModule
    -0.57
    éraire
    -0.53
    POSITIVE LOGITS
     ISNI
    0.50
    AppMethodBeat
    0.50
    ViewImports
    0.47
    AddWithValue
    0.46
    plass
    0.46
    Şi
    0.46
     entire
    0.45
    8
    0.45
    putstr
    0.45
    ūras
    0.45
    Activations Density 0.438%

    No Known Activations