© 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. 13513
    Prev
    Next
    INDEX
    Explanations

    text that covers some kind of conflict between groups of people

    oai_token-act-pair · gemini-2.0-flash

    political historical events, negativity

    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
    Negative Logits
     שוליים
    -0.71
    InitVars
    -0.60
    ingeki
    -0.57
     ComVisible
    -0.54
     Wiktionnaire
    -0.53
    таратура
    -0.53
     Pedersen
    -0.52
    ruzione
    -0.49
     getUsers
    -0.49
    ゅ
    -0.48
    POSITIVE LOGITS
    WriteTagHelper
    0.77
    Diweddarwch
    0.60
     &___
    0.54
    transQ
    0.54
    lorette
    0.53
     ModelExpression
    0.52
    /*++
    0.52
    contentLoaded
    0.52
    ądź
    0.50
     Allein
    0.50
    Activations Density 12.048%

    No Known Activations