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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9415
    Prev
    Next
    INDEX
    Explanations

    scientific jargon related to viral infection and immune response, particularly in the context of PRRSV

    oai_token-act-pair · gemini-2.0-flash

    immune response

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Antibodies
    -0.72
    AndEndTag
    -0.70
     immun
    -0.70
     antibodies
    -0.68
    Immun
    -0.67
    immun
    -0.67
    Antibodies
    -0.67
     Immune
    -0.66
    WebElementEntity
    -0.64
    ReusableCell
    -0.64
    POSITIVE LOGITS
    فسير
    0.49
    ecuzione
    0.49
    árl
    0.47
    وضوع
    0.46
    τέλε
    0.46
    قیمت
    0.46
     colonie
    0.46
    éviter
    0.45
     Verf
    0.44
     отредактировал
    0.44
    Activations Density 8.065%

    No Known Activations