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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8229
    Prev
    Next
    INDEX
    Explanations

    text related to sales and customer service, specifically discounts and engineering products

    oai_token-act-pair · gemini-2.0-flash

    Technical/bureaucratic texts

    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
     تضيفلها
    -0.81
    abestanden
    -0.73
     estekak
    -0.70
    ValueStyle
    -0.68
     AspNetCore
    -0.68
    RegistryLite
    -0.62
     defaultstate
    -0.62
    localctx
    -0.61
     متعلقه
    -0.61
    RectangleBorder
    -0.61
    POSITIVE LOGITS
     tasche
    0.53
     ρο
    0.52
    getTask
    0.52
    oluble
    0.49
    odied
    0.49
     menace
    0.49
    Chronicle
    0.49
    rotter
    0.48
     BOC
    0.48
    Version
    0.47
    Activations Density 0.574%

    No Known Activations