© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14632
    Prev
    Next
    INDEX
    Explanations

    mixed Malay/English text, and legal terms

    oai_token-act-pair · gemini-2.0-flash

    Malay language text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Cavendish
    -0.43
    ไตล์
    -0.43
     consegna
    -0.41
    licant
    -0.41
    gerton
    -0.40
     bile
    -0.40
    siv
    -0.40
     просмотра
    -0.40
     Ibarra
    -0.40
     Minerva
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.88
    ArgsConstructor
    0.75
    SequentialGroup
    0.75
     مشين
    0.68
     noqa
    0.68
    XtraBars
    0.68
    Бахар
    0.67
    IntoConstraints
    0.66
     चीज़ों
    0.66
    ніципалі
    0.65
    Activations Density 0.206%

    No Known Activations