© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14396
    Prev
    Next
    INDEX
    Explanations

    German and Lithuanian words, possibly surnames

    oai_token-act-pair · gemini-2.0-flash

    Different languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    orice
    -0.69
    ọi
    -0.67
    odotus
    -0.62
     /\.(
    -0.62
     tentative
    -0.60
     AssertionError
    -0.59
    MigrationBuilder
    -0.59
    ptonshire
    -0.59
     mannequin
    -0.59
     virtuelle
    -0.58
    POSITIVE LOGITS
    AnchorStyles
    0.62
    SaveChangesAsync
    0.56
     للاسماء
    0.56
    ously
    0.56
     HttpNotFound
    0.52
    Obrázky
    0.52
    Gweler
    0.51
    Quo
    0.50
     simplicité
    0.50
     لينك
    0.49
    Activations Density 0.377%

    No Known Activations