© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9003
    Prev
    Next
    INDEX
    Explanations

    the word "as" in various contexts, along with words appearing relative to it in the sentences.

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    تقاوى
    -0.72
     disambiguazione
    -0.66
    GEBURTSDATUM
    -0.64
     AssemblyCompany
    -0.64
    oredCriteria
    -0.56
    цезда
    -0.52
    displayquote
    -0.52
    postValue
    -0.51
     numberWith
    -0.51
    SourceChecksum
    -0.50
    POSITIVE LOGITS
     as
    3.39
     sebagai
    1.96
    作为
    1.59
    as
    1.59
     као
    1.53
     как
    1.49
    作為
    1.48
     ως
    1.47
     jako
    1.41
    sebagai
    1.38
    Activations Density 14.252%

    No Known Activations