© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11985
    Prev
    Next
    INDEX
    Explanations

    words used to describe a hospital or courtroom

    oai_token-act-pair · gemini-2.0-flash

    unusual or non-standard text elements

    np_token-act-pair-logits · gpt-4o-mini

    say rooms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    تقاوى
    -0.66
     channels
    -0.63
     autorytatywna
    -0.60
     кӀ
    -0.58
     offices
    -0.56
    FormTagHelper
    -0.56
    QUOTE
    -0.55
     <<<<<<<<<<<<<<
    -0.55
     centres
    -0.54
     wells
    -0.54
    POSITIVE LOGITS
    зулта
    0.61
    multer
    0.59
    ."));
    0.56
    "},
    0.55
     TextAppearance
    0.54
    djangoproject
    0.54
    neſs
    0.52
    🏾
    0.52
    .';
    0.51
    🏻‍♀️
    0.51
    Activations Density 1.043%

    No Known Activations