© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14760
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinals, especially when they're connected to food or a recipe

    oai_token-act-pair · gemini-2.0-flash

    pizza toppings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AsUp
    -0.73
    queryInterface
    -0.62
    fromnode
    -0.60
    ErrorException
    -0.60
    stateProvider
    -0.58
     newOwner
    -0.57
    audiovisuel
    -0.57
    انجليز
    -0.56
    Obrázky
    -0.56
     conduction
    -0.56
    POSITIVE LOGITS
     sausage
    0.47
     pizza
    0.44
     pretzels
    0.44
     pizzas
    0.44
     Pizza
    0.43
    🍔
    0.43
    +#+
    0.42
     burgers
    0.42
     buns
    0.42
     tacos
    0.42
    Activations Density 7.955%

    No Known Activations