© 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. 1264
    Prev
    Next
    INDEX
    Explanations

    legal and governmental language.

    oai_token-act-pair · gemini-2.0-flash

    legal and official contexts

    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
     nakalista
    -0.52
    resaid
    -0.49
     disambiguazione
    -0.49
     okuyayım
    -0.48
    ParallelGroup
    -0.47
    %;
    -0.44
    resultCode
    -0.44
    lename
    -0.43
    最快更新
    -0.43
     []).
    -0.42
    POSITIVE LOGITS
     ses
    0.59
     guarantees
    0.57
    super
    0.57
     Charters
    0.56
     Verfü
    0.56
    èses
    0.55
    MemoryWarning
    0.55
     reindeer
    0.55
    mejores
    0.55
    цезда
    0.54
    Activations Density 9.150%

    No Known Activations