© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "loop" generally in technical contexts

    oai_token-act-pair · gemini-2.0-flash

    loop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Theſe
    -0.94
    bibfield
    -0.92
     \\
    -0.91
    bibinfo
    -0.90
     whoſe
    -0.87
     Monfieur
    -0.85
     Савезне
    -0.85
    >\<^
    -0.84
     الحره
    -0.82
     purpoſe
    -0.81
    POSITIVE LOGITS
    antd
    0.58
    dotenv
    0.55
    äsident
    0.54
     Pon
    0.53
    scriptcase
    0.52
    ERP
    0.51
     pon
    0.51
     falt
    0.51
    Uni
    0.50
     säkert
    0.50
    Activations Density 1.920%

    No Known Activations