© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1285
    Prev
    Next
    INDEX
    Explanations

    marketing promotions for Mario Badescu products

    oai_token-act-pair · gemini-2.0-flash

    Coupon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     repeatedly
    -0.44
     Bri
    -0.41
    涌
    -0.41
     pistola
    -0.40
    <eos>
    -0.39
     cope
    -0.39
     benefits
    -0.38
     се
    -0.37
     lat
    -0.36
    LA
    -0.36
    POSITIVE LOGITS
    OGND
    0.81
    IUrlHelper
    0.78
     disambiguazione
    0.78
    yntaxException
    0.76
     estimés
    0.75
     consultato
    0.74
     betweenstory
    0.74
    DockStyle
    0.72
     Monfieur
    0.72
    Cyfeiriadau
    0.70
    Activations Density 0.528%

    No Known Activations