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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13828
    Prev
    Next
    INDEX
    Explanations

    text discussing societal expectations or norms and people's adherence to them

    oai_token-act-pair · gemini-2.0-flash

    Women in society

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    enumi
    -0.67
     Wikimédia
    -0.63
     virtuel
    -0.55
     المعيارى
    -0.54
    clonal
    -0.51
    ApiModel
    -0.49
     InputDecoration
    -0.48
     TextInputType
    -0.48
    ExtendWith
    -0.48
    الحياه
    -0.47
    POSITIVE LOGITS
    omeness
    0.63
    :✨
    0.59
     worldly
    0.58
    Américaine
    0.57
     domestic
    0.56
    oredCriteria
    0.56
    "])){
    0.56
    GINS
    0.56
    WriteTagHelper
    0.56
    ursday
    0.55
    Activations Density 2.738%

    No Known Activations