© 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. 2051
    Prev
    Next
    INDEX
    Explanations

    words related to dark vs light, size comparison, beams and mask creation in relation to manufacturing a device and/or in calculating kernals.

    oai_token-act-pair · gemini-2.0-flash

    gradations

    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
     transfieras
    -0.84
    IUrlHelper
    -0.74
     تضيفلها
    -0.71
     propOrder
    -0.71
    parsedMessage
    -0.66
    GEBURTSDATUM
    -0.66
    TintMode
    -0.65
     متعلقه
    -0.65
    NameInMap
    -0.64
    ReusableCell
    -0.63
    POSITIVE LOGITS
    ⓧ
    0.51
     ביותר
    0.47
    extend
    0.47
    endforeach
    0.47
     maxn
    0.44
    Ext
    0.43
    pplung
    0.42
     Extre
    0.42
    故
    0.42
     extent
    0.42
    Activations Density 2.528%

    No Known Activations