© 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. 13988
    Prev
    Next
    INDEX
    Explanations

    terms from advanced statistical analysis and scientific forecasting

    oai_token-act-pair · gemini-2.0-flash

    Mathematical/statistical texts

    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
    cabulary
    -0.50
    providedIn
    -0.49
     rospy
    -0.47
    quilibrium
    -0.47
    ngrx
    -0.47
    kräf
    -0.45
     teil
    -0.45
     Juga
    -0.44
    ẨM
    -0.44
    zaamheid
    -0.43
    POSITIVE LOGITS
    StoryboardSegue
    0.83
    EndGlobalSection
    0.69
     '\\;'
    0.68
    şiv
    0.67
    rungsseite
    0.66
     useAppContext
    0.65
     Италијани
    0.61
     pound
    0.61
    цездатний
    0.60
     חיצוניים
    0.60
    Activations Density 4.771%

    No Known Activations