© 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. 219
    Prev
    Next
    INDEX
    Explanations

    ingredients and dishes, often associated with Middle Eastern cuisine, and salads

    oai_token-act-pair · gemini-2.0-flash

    salad

    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
    abestanden
    -0.72
     оригіналу
    -0.70
    ftagPool
    -0.69
    guten
    -0.68
    fml
    -0.64
     arşivlendi
    -0.63
     lenker
    -0.63
    fitrión
    -0.61
    tispiece
    -0.59
    Referanser
    -0.58
    POSITIVE LOGITS
    IContainer
    0.50
    Viitteet
    0.49
    ığımız
    0.44
    ViewFeatures
    0.42
    PhysRev
    0.42
    pageY
    0.42
    >({
    0.41
     miembros
    0.41
    lož
    0.40
    ığım
    0.39
    Activations Density 1.282%

    No Known Activations