© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8280
    Prev
    Next
    INDEX
    Explanations

    German text that uses a variety of punctuation marks and sentence structures

    oai_token-act-pair · gemini-2.0-flash

    complex sentence structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    awtextra
    -0.82
     ostavi
    -0.62
    atrième
    -0.57
    Становништво
    -0.57
     Polis
    -0.56
     Obl
    -0.55
    +#+
    -0.51
     Otta
    -0.50
    ObjectModel
    -0.50
    Sucesor
    -0.49
    POSITIVE LOGITS
    onomía
    0.60
     Paglinawan
    0.53
    ایج
    0.52
     herein
    0.51
     ReactDOM
    0.47
    tım
    0.45
    LabelTagHelper
    0.44
    Browse
    0.44
    VIAF
    0.44
    AndFlush
    0.44
    Activations Density 0.549%

    No Known Activations