© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7032
    Prev
    Next
    INDEX
    Explanations

    German language related words.

    oai_token-act-pair · gemini-2.0-flash

    Foreign 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_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
    ]--;
    -0.79
     препратки
    -0.71
     متعلقه
    -0.67
     propOrder
    -0.65
    parsedMessage
    -0.65
    сылкі
    -0.65
    QMetaType
    -0.63
     Baillargeon
    -0.63
    InputTagHelper
    -0.62
    RenderAtEndOf
    -0.62
    POSITIVE LOGITS
     vectoriales
    0.56
     elettrico
    0.55
     brancas
    0.54
     hvit
    0.53
     experiências
    0.52
     všetkých
    0.51
    Vladimir
    0.50
     pauvres
    0.50
     všem
    0.50
     mesmas
    0.50
    Activations Density 1.035%

    No Known Activations