© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10865
    Prev
    Next
    INDEX
    Explanations

    the character string "nog" or "g[single character]"

    oai_token-act-pair · gemini-2.0-flash

    European languages & names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    出版年
    -0.70
    PerformLayout
    -0.62
    الإنجليزية
    -0.53
     незавершена
    -0.51
    GEBURTSDATUM
    -0.48
     HttpNotFound
    -0.48
    WithIOException
    -0.47
     chrétiens
    -0.46
    TagMode
    -0.46
     gawas
    -0.46
    POSITIVE LOGITS
     informée
    0.66
     whereof
    0.57
    multer
    0.55
     Racine
    0.54
     insensible
    0.54
    clusal
    0.53
    testcase
    0.52
     eventdata
    0.52
     GenerationType
    0.52
    chauer
    0.52
    Activations Density 0.309%

    No Known Activations