© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7354
    Prev
    Next
    INDEX
    Explanations

    the phrase "as a" followed by a noun or adjective

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    Negative Logits
    Chham
    -0.72
    InteropServices
    -0.63
     referenties
    -0.59
    )‏
    -0.59
    UiThread
    -0.59
    GraphicsUnit
    -0.57
    ContextHolder
    -0.57
     betweenstory
    -0.57
    NewUrlParser
    -0.56
     OnTriggerEnter
    -0.56
    POSITIVE LOGITS
     matter
    0.79
    Obrázky
    0.68
     direct
    0.60
     MATTER
    0.54
    Hauptartikel
    0.54
     DIRECT
    0.53
    matter
    0.52
    direct
    0.52
     Matter
    0.52
    Hentet
    0.49
    Activations Density 1.540%

    No Known Activations