© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12322
    Prev
    Next
    INDEX
    Explanations

    names of Asian foods and restaurants

    oai_token-act-pair · gemini-2.0-flash

    Asian food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    APN
    -0.55
     nakalista
    -0.48
     aeration
    -0.47
    bewerken
    -0.46
    entis
    -0.46
    ]._
    -0.46
    яс
    -0.45
     bağlantılar
    -0.45
    __((
    -0.44
     aérienne
    -0.44
    POSITIVE LOGITS
    VersionUID
    0.63
    isContained
    0.60
     Allociné
    0.57
    QUADS
    0.52
    NewGuid
    0.52
     وتسجيلات
    0.52
    RTGC
    0.52
    }{*}{
    0.51
     TestBed
    0.49
    blica
    0.49
    Activations Density 3.563%

    No Known Activations