© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9629
    Prev
    Next
    INDEX
    Explanations

    interjections and sounds of hesitation or acknowledgment

    oai_token-act-pair · gemini-2.0-flash

    interjections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Anſ
    -0.59
    ГЛА
    -0.57
    +/**
    -0.54
    envol
    -0.54
    nościo
    -0.53
     Theſe
    -0.52
     Fø
    -0.52
     Diſ
    -0.51
    }(),
    -0.49
    FXMLLoader
    -0.49
    POSITIVE LOGITS
    WireFormat
    0.75
    TintMode
    0.69
    SourceChecksum
    0.63
    quelize
    0.59
     ostavi
    0.59
     disambiguazione
    0.56
     Ahh
    0.55
    Hmmm
    0.55
    mmmm
    0.55
     ویکی‌پدی
    0.54
    Activations Density 0.593%

    No Known Activations