© 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. 2886
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly random short sequences of characters, possibly including misspellings or non-English words

    oai_token-act-pair · gemini-2.0-flash

    jewelry or clothing

    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
     يتيمه
    -0.92
    Autoritní
    -0.90
    Rüyada
    -0.81
    LookAnd
    -0.72
    RenderAtEndOf
    -0.71
     متعلقه
    -0.66
    はじめに
    -0.65
     Walkover
    -0.64
    dersfield
    -0.63
    сылкі
    -0.62
    POSITIVE LOGITS
     kılıf
    0.93
     küpe
    0.88
     bileklik
    0.87
     yüzük
    0.85
     taşlı
    0.81
     kolye
    0.80
     kağıdı
    0.79
     çantası
    0.78
     elbise
    0.77
     sırt
    0.77
    Activations Density 2.225%

    No Known Activations