© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5068
    Prev
    Next
    INDEX
    Explanations

    words related to viruses, diseases and shifts

    oai_token-act-pair · gemini-2.0-flash

    Viruses and shifts

    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
    AddTagHelper
    -1.24
    MigrationBuilder
    -1.17
    mybatisplus
    -1.12
    ftagPool
    -1.07
     MainAxisSize
    -1.05
    клопе
    -1.02
    ConstraintMaker
    -1.02
     kasarigan
    -0.99
     ComVisible
    -0.96
     ویکی‌پدی
    -0.92
    POSITIVE LOGITS
    htra
    0.59
     ist
    0.59
    ("%
    0.56
    ган
    0.56
    textrm
    0.55
     Des
    0.53
     est
    0.53
    isu
    0.52
     sind
    0.52
     principal
    0.51
    Activations Density 0.763%

    No Known Activations