© 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. 523
    Prev
    Next
    INDEX
    Explanations

    Danish language words, especially those in legal or historical contexts

    oai_token-act-pair · 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
     propOrder
    -0.52
     estekak
    -0.49
     незавершена
    -0.48
    Autoritní
    -0.42
    WebVitals
    -0.41
     transfieras
    -0.40
    Tikang
    -0.38
     disambiguazione
    -0.36
     مُعرِّف
    -0.36
     lenker
    -0.35
    POSITIVE LOGITS
     Agamemnon
    0.64
     Moroccan
    0.59
     Dante
    0.59
     Cervantes
    0.59
     Mino
    0.58
     Nea
    0.57
     Croatian
    0.57
     Lorca
    0.57
     Algerian
    0.57
     Lebanese
    0.57
    Activations Density 2.061%

    No Known Activations