© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11157
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to detection of pathogens and potential harm

    oai_token-act-pair · gemini-2.0-flash

    detection of diseases, contamination

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyCulture
    -0.63
    مصادر
    -0.52
    glEnd
    -0.52
    Cite
    -0.52
    
    -0.51
     Karn
    -0.50
    IMDG
    -0.50
    MENAFN
    -0.50
    toral
    -0.47
    RetentionPolicy
    -0.47
    POSITIVE LOGITS
    DrawerToggle
    0.60
     microp
    0.54
     crois
    0.54
    tanleria
    0.54
     defaultstate
    0.53
     poffible
    0.51
     washing
    0.50
     Washing
    0.50
     contaminated
    0.49
    mic
    0.49
    Activations Density 1.509%

    No Known Activations