© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1748
    Prev
    Next
    INDEX
    Explanations

    discussion about women and equality, especially in the context of Marvel comics and superhero representation.

    oai_token-act-pair · gemini-2.0-flash

    Sexism and population

    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
     ivelany
    -0.60
    yntaxException
    -0.54
    Mine
    -0.48
     Италијани
    -0.47
    kuuta
    -0.47
    Хьажоргаш
    -0.47
     gjelder
    -0.47
     maschile
    -0.45
    <tfoot>
    -0.44
    cipais
    -0.43
    POSITIVE LOGITS
    ollectionView
    0.59
    🏻
    0.58
    NameInMap
    0.55
    ⓘ
    0.54
    WriteTagHelper
    0.53
    تقاوى
    0.52
    LookAnd
    0.52
    IUrlHelper
    0.52
    ंदीखरीदारी
    0.51
    🏼
    0.51
    Activations Density 51.180%

    No Known Activations