© 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. 3884
    Prev
    Next
    INDEX
    Explanations

    words related to commerce, particularly pricing, tariffs or taxes

    oai_token-act-pair · gemini-2.0-flash

    price

    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
    GEBURTSDATUM
    -0.84
    出版年
    -0.76
    Билгалдахарш
    -0.75
     ujednoznacz
    -0.63
    CodeAttribute
    -0.62
    ⓧ
    -0.57
     @"/
    -0.55
    urlopen
    -0.55
    currentColor
    -0.54
    WebVitals
    -0.53
    POSITIVE LOGITS
    findpost
    0.67
    obox
    0.51
    OPO
    0.48
    FieldBuilder
    0.48
     Platinum
    0.47
     Wird
    0.46
     GE
    0.46
     traitors
    0.46
     Soll
    0.45
    WindowEvent
    0.45
    Activations Density 2.698%

    No Known Activations