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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5156
    Prev
    Next
    INDEX
    Explanations

    the word 'as' preceded or followed by another word

    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_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
     disambiguazione
    -0.94
    WithIOException
    -0.81
     Signalez
    -0.79
    IUrlHelper
    -0.68
    ViewImports
    -0.66
    
    -0.65
    AndEndTag
    -0.65
    ChildScrollView
    -0.60
    queryInterface
    -0.60
     HasFactory
    -0.59
    POSITIVE LOGITS
     moment
    1.88
     minute
    1.65
     as
    1.64
    moment
    1.58
     soon
    1.56
     Moment
    1.45
    Moment
    1.34
     MOMENT
    1.25
    minute
    1.23
    soon
    1.22
    Activations Density 1.171%

    No Known Activations