© 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. 12173
    Prev
    Next
    INDEX
    Explanations

    words that are common grammatical function words, especially those that are pronouns or auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    code/technical context

    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
    useNewUrlParser
    -0.48
     autant
    -0.47
    PKG
    -0.47
    SharedCtor
    -0.47
    いう
    -0.46
    Erreferentziak
    -0.43
    toma
    -0.43
    Weblinks
    -0.42
    Brace
    -0.41
     jäl
    -0.41
    POSITIVE LOGITS
     fieldNum
    0.74
    GraphicsUnit
    0.73
     eventdata
    0.68
    XtraReports
    0.67
     GetEnumerator
    0.66
     resourceCulture
    0.64
    AndEndTag
    0.63
     ProtoMessage
    0.62
    henswürdigkeiten
    0.60
    AutoresizingMask
    0.60
    Activations Density 1.358%

    No Known Activations