© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4743
    Prev
    Next
    INDEX
    Explanations

    the word "applications"

    oai_token-act-pair · gemini-2.0-flash

    applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     application
    -0.81
     applications
    -0.78
    application
    -0.75
    ode
    -0.61
    вери
    -0.60
     Applications
    -0.59
    ाम
    -0.59
    固
    -0.57
     announcement
    -0.57
    ys
    -0.57
    POSITIVE LOGITS
     Réponses
    1.17
     autorytatywna
    1.15
    تقاوى
    1.04
     ModelExpression
    1.03
    Personensuche
    1.01
     kasarigan
    0.97
    aarrggbb
    0.96
    GOTREF
    0.95
     незавершена
    0.95
     betweenstory
    0.95
    Activations Density 0.482%

    No Known Activations