© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4253
    Prev
    Next
    INDEX
    Explanations

    a mix of proper nouns, especially those relating to a specific geographic location, error codes relating to linking, and Spanish language verbs

    oai_token-act-pair · gemini-2.0-flash

    location names or geographic 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
    tagHelperRunner
    -1.11
    parsedMessage
    -0.94
     '\\;'
    -0.91
    protoimpl
    -0.81
     initComponents
    -0.79
    SpringBootTest
    -0.76
     oprot
    -0.75
    IUrlHelper
    -0.75
    endphp
    -0.75
    ंदीखरीदारी
    -0.74
    POSITIVE LOGITS
    ecta
    0.41
     population
    0.41
     panel
    0.40
    sop
    0.40
    Ư
    0.40
     mal
    0.39
    étend
    0.38
     său
    0.38
     ihr
    0.38
    ných
    0.37
    Activations Density 0.394%

    No Known Activations