© 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. 11969
    Prev
    Next
    INDEX
    Explanations

    words within academic papers and technical documentation

    oai_token-act-pair · gemini-2.0-flash

    programming and data structures

    np_token-act-pair-logits · gpt-4o-mini
    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
     containing
    -1.70
     contains
    -1.59
     contain
    -1.59
     Containing
    -1.59
     Contain
    -1.49
     Contains
    -1.46
     includes
    -1.41
    contains
    -1.39
    contain
    -1.39
    containing
    -1.38
    POSITIVE LOGITS
    findpost
    0.60
     createState
    0.47
    الدراسه
    0.47
    EndInit
    0.47
    RectangleBorder
    0.46
     jsPsych
    0.45
     indépendante
    0.45
     Paglinawan
    0.45
    jutant
    0.44
     تضيفلها
    0.41
    Activations Density 1.181%

    No Known Activations