© 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. 8390
    Prev
    Next
    INDEX
    Explanations

    references to wealth and lavish lifestyles

    oai_token-act-pair · gemini-2.0-flash

    luxury

    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
     luxury
    -2.58
     Luxury
    -2.31
    luxury
    -2.28
    Luxury
    -2.22
     luxurious
    -2.02
     luxe
    -1.91
     Luxus
    -1.87
     LUX
    -1.80
     lux
    -1.80
     lujo
    -1.68
    POSITIVE LOGITS
    unie
    0.50
    detto
    0.48
     predictable
    0.48
    Eksterne
    0.45
     <>",
    0.44
    redients
    0.44
    prometheus
    0.43
     castellano
    0.43
    hawar
    0.41
    mediaPlayer
    0.41
    Activations Density 2.250%

    No Known Activations