© 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. 3678
    Prev
    Next
    INDEX
    Explanations

    uses of the word "as" connected to other words related to math, science, and data analysis

    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
    ########.
    -0.71
     للمعارف
    -0.69
     destinées
    -0.66
    ValueStyle
    -0.65
    GraphicsUnit
    -0.63
     Roskov
    -0.63
    RegressionTest
    -0.63
     réguli
    -0.62
     lenker
    -0.62
     malades
    -0.61
    POSITIVE LOGITS
     experienced
    0.46
     returns
    0.45
     CIS
    0.45
     Jir
    0.44
    animous
    0.43
    onAttach
    0.43
     a
    0.43
    tick
    0.43
    AB
    0.43
     AGB
    0.42
    Activations Density 12.851%

    No Known Activations