© 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. 4687
    Prev
    Next
    INDEX
    Explanations

    numbers, especially dates

    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
    ">//
    -0.44
    佗
    -0.43
     surla
    -0.43
    DropColumn
    -0.43
     Пусть
    -0.41
    着
    -0.41
    愷
    -0.40
    Surface
    -0.39
    toarele
    -0.39
    EnableWeb
    -0.38
    POSITIVE LOGITS
     estekak
    0.69
     pinulongan
    0.68
     للمعارف
    0.66
     cjs
    0.61
    +#+#
    0.60
    PreExecute
    0.59
    +#+
    0.58
    DataSnapshot
    0.58
     jsPsych
    0.57
    ServletRequest
    0.57
    Activations Density 4.932%

    No Known Activations