© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7214
    Prev
    Next
    INDEX
    Explanations

    passages related to religious rituals and objects

    oai_token-act-pair · gemini-2.0-flash

    Random snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    rrggbb
    -0.70
    Personendaten
    -0.66
     GenerationType
    -0.65
    Personensuche
    -0.62
     مشين
    -0.62
     otomatig
    -0.60
    CloseOperation
    -0.60
     Taktlose
    -0.57
    出版年
    -0.56
     мәкал
    -0.56
    POSITIVE LOGITS
    달
    0.51
    stylesheet
    0.50
     مرجع
    0.48
    chery
    0.47
    étrie
    0.47
    ggplot
    0.47
     marketer
    0.45
     lệ
    0.45
    Willkommen
    0.45
    hez
    0.45
    Activations Density 0.131%

    No Known Activations