© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    words related to food courts, restaurants, and dining

    oai_token-act-pair · gemini-2.0-flash

    court

    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
     مخطط
    -0.46
    nao
    -0.45
     perlu
    -0.45
    giro
    -0.42
     jornadas
    -0.40
    iniz
    -0.40
    oni
    -0.40
    gam
    -0.39
    pä
    -0.39
     lbl
    -0.38
    POSITIVE LOGITS
    RegistryLite
    0.83
    StoryboardSegue
    0.70
    FontOfSize
    0.66
    LookAnd
    0.66
    شهاد
    0.65
    DockStyle
    0.63
    省市镇
    0.60
     Wiktionnaire
    0.60
     كورة
    0.60
    CPtr
    0.59
    Activations Density 0.631%

    No Known Activations