© 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. 14687
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to viruses and antiviral treatments

    oai_token-act-pair · gemini-2.0-flash

    treatments

    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
    hoben
    -0.52
    "]]
    -0.49
    bray
    -0.48
    PyExc
    -0.47
     nonatomic
    -0.46
    FormTagHelper
    -0.46
    órc
    -0.45
     Jep
    -0.45
    liffe
    -0.45
    円
    -0.43
    POSITIVE LOGITS
     treatments
    0.74
    sizeCache
    0.65
    Treatments
    0.64
    ModelAdmin
    0.64
     treatment
    0.64
     Treatments
    0.63
    ListItemIcon
    0.59
     calendriers
    0.57
    ConstraintMaker
    0.57
     traitements
    0.56
    Activations Density 4.496%

    No Known Activations