© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3683
    Prev
    Next
    INDEX
    Explanations

    words that relate to people and possibly borders

    oai_token-act-pair · gemini-2.0-flash

    women and citizens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nahilalakip
    -0.80
     ***!
    -0.71
    httphttps
    -0.69
     مشين
    -0.66
    WindowConstants
    -0.65
    __(/*!
    -0.65
     Pesquisa
    -0.58
    mstyle
    -0.56
     Kraken
    -0.55
     okhttp
    -0.55
    POSITIVE LOGITS
    ",$
    0.80
    MLLoader
    0.77
    metery
    0.70
     nothwendig
    0.70
    windowFixed
    0.68
    quele
    0.67
    полне
    0.67
    jenigen
    0.67
    ์ตูน
    0.67
    cèse
    0.66
    Activations Density 1.524%

    No Known Activations