© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5120
    Prev
    Next
    INDEX
    Explanations

    numbers, specifically quantities of things

    oai_token-act-pair · gemini-2.0-flash

    uncommon or foreign terms and identifiers

    np_token-act-pair-logits · gpt-4o-mini
    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
    ArrowToggle
    -0.67
     or
    -0.55
     spiega
    -0.51
    reactstrap
    -0.50
    labelledby
    -0.47
     unknownFields
    -0.46
    msgSender
    -0.45
     под
    -0.45
     resourceCulture
    -0.44
     Bonner
    -0.44
    POSITIVE LOGITS
     Waray
    0.74
    abestanden
    0.70
    /*
    0.65
     Résultats
    0.62
    InjectAttribute
    0.57
     rhestr
    0.57
    complexContent
    0.57
    /**
    0.57
    VersionUID
    0.55
     Exacts
    0.54
    Activations Density 2.504%

    No Known Activations