© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15073
    Prev
    Next
    INDEX
    Explanations

    words that relate to pathogens and parasites

    oai_token-act-pair · gemini-2.0-flash

    terms related to pathogens and infectious agents

    np_token-act-pair-logits · gpt-4o-mini

    pathogens and infections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Pythagoras
    -0.76
     Shakspeare
    -0.75
     TextInputType
    -0.70
    Hochspringen
    -0.69
    picasso
    -0.68
     <=",
    -0.68
     بيها
    -0.65
    MLLoader
    -0.65
     Shaksp
    -0.63
     ſy
    -0.63
    POSITIVE LOGITS
     par
    0.60
     agents
    0.52
     living
    0.50
     para
    0.50
     agent
    0.49
     Par
    0.47
    soa
    0.47
     parar
    0.47
     Wiktionnaire
    0.47
     micro
    0.45
    Activations Density 1.588%

    No Known Activations