© 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. 8770
    Prev
    Next
    INDEX
    Explanations

    descriptions of businesses, especially small local businesses, and words related to sales

    oai_token-act-pair · gemini-2.0-flash

    bus

    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
    aarrggbb
    -0.92
    RenderAtEndOf
    -0.86
    businesses
    -0.86
    Businesses
    -0.83
     >=",
    -0.82
     '\\;'
    -0.82
    lorette
    -0.81
     Businesses
    -0.78
     Comercial
    -0.77
    IndentedString
    -0.77
    POSITIVE LOGITS
     bus
    1.38
     Bus
    1.27
    Bus
    1.23
    bus
    1.17
     small
    1.05
    Small
    1.01
     bu
    0.99
    small
    0.99
     Small
    0.93
    BUS
    0.92
    Activations Density 1.300%

    No Known Activations