© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2901
    Prev
    Next
    INDEX
    Explanations

    words related to automotive technology and hybrid/electric vehicles

    oai_token-act-pair · gemini-2.0-flash

    hybrid electric vehicles

    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
     kiin
    -0.52
    miral
    -0.48
     BoxDecoration
    -0.47
    kirakan
    -0.47
    baiki
    -0.47
     resultCode
    -0.46
     garanzia
    -0.45
     personalità
    -0.45
     exécu
    -0.45
     spedizione
    -0.43
    POSITIVE LOGITS
     Roskov
    0.83
    sizeCache
    0.80
    WriteTagHelper
    0.74
    XmlEnum
    0.65
     AssemblyTitle
    0.64
    Hentet
    0.63
     Audiodateien
    0.63
     esternos
    0.60
    DECREF
    0.60
     ostavi
    0.59
    Activations Density 1.157%

    No Known Activations