© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13607
    Prev
    Next
    INDEX
    Explanations

    mentions of patients with limited English proficiency or comparisons of English-only, bilingual, and limited English proficiency populations.

    oai_token-act-pair · gemini-2.0-flash

    Language translations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     translation
    -2.14
     translated
    -2.14
     translate
    -2.09
     translating
    -2.00
     translations
    -1.96
     Translation
    -1.93
    Translation
    -1.88
    translated
    -1.83
     translator
    -1.79
    translation
    -1.78
    POSITIVE LOGITS
    providedIn
    0.59
    ゴリー
    0.44
    misu
    0.42
     diện
    0.42
    yll
    0.41
    iffa
    0.40
    Hochspringen
    0.40
    ParallelGroup
    0.40
     peppa
    0.40
     Daun
    0.39
    Activations Density 1.522%

    No Known Activations