© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15928
    Prev
    Next
    INDEX
    Explanations

    sensory and preparation vocabulary related to food products, recipes, and harvesting

    oai_token-act-pair · gemini-2.0-flash

    date

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    脚注の使い方
    -0.79
     actionMode
    -0.67
    RSpec
    -0.59
    seigneur
    -0.59
    homonymie
    -0.58
    //</
    -0.58
     Ceramby
    -0.58
    ==",
    -0.57
    arabe
    -0.57
    ]")]
    -0.56
    POSITIVE LOGITS
     dates
    1.04
     date
    0.96
     Dates
    0.87
     Date
    0.82
    dates
    0.80
     DATES
    0.78
    date
    0.78
     DATE
    0.75
    Date
    0.74
    DATE
    0.73
    Activations Density 4.081%

    No Known Activations