© 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. 2891
    Prev
    Next
    INDEX
    Explanations

    terms related to aviation regulations and the act of flying at night

    oai_token-act-pair · gemini-2.0-flash

    flight operations

    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
    AnchorStyles
    -0.59
    DebuggerNonUser
    -0.58
    XmlAccessType
    -0.56
    ineno
    -0.54
    enumii
    -0.53
    شهاد
    -0.53
    #+#
    -0.51
     खरीदा
    -0.47
    hamcrest
    -0.46
    nictví
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.68
     TEMPO
    0.62
    webElement
    0.62
     disambiguazione
    0.60
     متعلقه
    0.56
     ویکی‌پدیا
    0.56
     cold
    0.56
    ungguhnya
    0.56
     ground
    0.56
     IBOutlet
    0.55
    Activations Density 1.209%

    No Known Activations