© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 80
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to highway interchanges

    oai_token-act-pair · gemini-2.0-flash

    merge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    UnitTesting
    -0.90
    SourceChecksum
    -0.71
     beginnetje
    -0.71
     незавершена
    -0.69
    wnież
    -0.66
    AndroidJUnit
    -0.65
    IndentedString
    -0.65
    reportWebVitals
    -0.64
     pinulongan
    -0.64
    يكب
    -0.64
    POSITIVE LOGITS
     Sinal
    0.52
     Vlas
    0.50
    ultas
    0.48
    Itoa
    0.46
    ModelMap
    0.46
    Revis
    0.46
     LIBRA
    0.46
    ebly
    0.46
     Antelope
    0.45
    ativité
    0.44
    Activations Density 0.664%

    No Known Activations