© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5260
    Prev
    Next
    INDEX
    Explanations

    words relating to wireless internet and frequencies

    oai_token-act-pair · gemini-2.0-flash

    Wireless and radio signals

    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
     EconPapers
    -0.96
     CreateTagHelper
    -0.92
    تقاوى
    -0.90
    cipar
    -0.86
    Portale
    -0.84
    DoubleQuotes
    -0.82
     kaarangay
    -0.80
    addCriterion
    -0.74
    endpush
    -0.74
    interopRequire
    -0.73
    POSITIVE LOGITS
    нологі
    0.54
    bouncycastle
    0.50
     localObject
    0.47
     Mord
    0.45
    uvo
    0.43
     MERCHANTABILITY
    0.41
     marge
    0.41
     Ly
    0.40
     sem
    0.39
    όμε
    0.38
    Activations Density 0.532%

    No Known Activations