© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10067
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and associated verb tenses.

    oai_token-act-pair · gemini-2.0-flash

    I

    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
    Go
    -0.48
     EconPapers
    -0.46
    lev
    -0.46
     Go
    -0.43
    om
    -0.42
    issau
    -0.41
    link
    -0.41
    ville
    -0.40
    편
    -0.40
     Carey
    -0.39
    POSITIVE LOGITS
    IonicModule
    0.68
    ValueStyle
    0.68
    mybatisplus
    0.67
    帖最后由
    0.64
     MenuView
    0.63
     AssemblyCulture
    0.62
     LoggerFactory
    0.62
    Hauptartikel
    0.61
     betweenstory
    0.61
     HttpNotFound
    0.61
    Activations Density 0.487%

    No Known Activations