© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10888
    Prev
    Next
    INDEX
    Explanations

    mentions of colleges and universities

    oai_token-act-pair · gemini-2.0-flash

    colleges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     college
    -0.87
     College
    -0.81
     autorytatywna
    -0.77
     university
    -0.76
     universitario
    -0.75
     kuliah
    -0.75
    College
    -0.74
     COLLEGE
    -0.73
    college
    -0.73
     University
    -0.73
    POSITIVE LOGITS
     digitale
    0.45
     digitized
    0.43
    Viited
    0.42
    NameInMap
    0.42
    raded
    0.42
     Unsc
    0.41
     children
    0.41
     Children
    0.41
    Poloha
    0.41
    RoutingModule
    0.40
    Activations Density 1.122%

    No Known Activations