© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13211
    Prev
    Next
    INDEX
    Explanations

    references to young people in relation to politics or artistic talent

    oai_token-act-pair · gemini-2.0-flash

    young

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     young
    -1.15
    young
    -1.06
     youth
    -1.02
    youth
    -0.97
     Young
    -0.94
    Young
    -0.93
     Youth
    -0.90
     youthful
    -0.90
    Youth
    -0.86
     YOUNG
    -0.86
    POSITIVE LOGITS
     createState
    0.77
    الحياه
    0.73
    protoimpl
    0.73
    tagHelperRunner
    0.69
    erapeutics
    0.65
    Diweddarwch
    0.60
     $_"
    0.59
    ^(@)
    0.59
    adaptiveStyles
    0.57
    monary
    0.56
    Activations Density 5.519%

    No Known Activations