© 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. 6468
    Prev
    Next
    INDEX
    Explanations

    the word "as" followed by other words

    oai_token-act-pair · gemini-2.0-flash

    technical terms or coding syntax

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

    as

    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
    الإنجليزية
    -0.45
     drop
    -0.44
    εβ
    -0.43
    Rüyada
    -0.43
    WebServlet
    -0.42
     mark
    -0.41
    navigationBar
    -0.41
     numberWith
    -0.41
     emprunt
    -0.41
    ⇑
    -0.40
    POSITIVE LOGITS
     ioutil
    0.66
    XmlAccessorType
    0.65
     propOrder
    0.63
    BeginContext
    0.63
    Geplaatst
    0.62
    tagHelperRunner
    0.60
    theoremstyle
    0.59
     AssemblyTitle
    0.59
     actionMode
    0.59
     المعيارى
    0.58
    Activations Density 0.336%

    No Known Activations