© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15964
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are Swedish

    oai_token-act-pair · gemini-2.0-flash

    Swedish language/references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    TagMode
    -0.73
    ValueStyle
    -0.71
    躇
    -0.65
     invitamos
    -0.62
    CodedInputStream
    -0.59
     ComVisible
    -0.57
     kasarigan
    -0.57
     defaultstate
    -0.57
     viewDidLoad
    -0.56
    хьтан
    -0.56
    POSITIVE LOGITS
    arde
    0.55
     ý
    0.52
    CppCodeGen
    0.50
     Вікіпе
    0.50
    mander
    0.49
    lations
    0.48
    gerne
    0.47
    larna
    0.47
     &___
    0.47
    adis
    0.46
    Activations Density 2.515%

    No Known Activations