© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10910
    Prev
    Next
    INDEX
    Explanations

    passages related to marine biology, especially anything about sharks and/or oceanographic surveys

    oai_token-act-pair · gemini-2.0-flash

    autorytatywna

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     sea
    -1.13
     seawater
    -1.07
     ocean
    -1.02
     coastal
    -1.01
     marine
    -0.96
     seaside
    -0.95
     beach
    -0.95
     Coastal
    -0.91
     maritime
    -0.91
     seashore
    -0.91
    POSITIVE LOGITS
     autorytatywna
    0.60
    PhysRevD
    0.59
     AssemblyCompany
    0.57
     Biele
    0.56
    SequentialGroup
    0.56
     DSA
    0.54
    Abit
    0.53
     Slovakia
    0.52
     CommonModule
    0.52
     HSA
    0.51
    Activations Density 0.396%

    No Known Activations