© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 601
    Prev
    Next
    INDEX
    Explanations

    code snippets and text in languages other than English (Malay and Portuguese)

    oai_token-act-pair · gemini-2.0-flash

    code mixed with other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     itſelf
    -0.97
     greateſt
    -0.96
     pleaſure
    -0.93
     Jefus
    -0.93
     myſelf
    -0.90
     propOrder
    -0.88
     Efq
    -0.88
     Majefty
    -0.87
    ſelves
    -0.85
     becauſe
    -0.85
    POSITIVE LOGITS
     me
    0.74
     mình
    0.58
     си
    0.54
     our
    0.54
    PrototypeOf
    0.52
     فريبيس
    0.49
     you
    0.48
    我
    0.47
    GEBURTSDATUM
    0.47
     خود
    0.46
    Activations Density 0.160%

    No Known Activations