© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15277
    Prev
    Next
    INDEX
    Explanations

    references to ages or centuries

    oai_token-act-pair · gemini-2.0-flash

    IUrlHelper

    np_max-act-logits · gemini-2.0-flash

    ▁

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     démocr
    -0.30
    2
    -0.27
    3
    -0.26
    1
    -0.26
     langues
    -0.26
    8
    -0.24
     campion
    -0.24
     lauk
    -0.24
     económica
    -0.24
    ↵
    -0.24
    POSITIVE LOGITS
    IUrlHelper
    0.89
     ―――――
    0.89
    \<^
    0.88
    
    0.87
    ſelf
    0.86
    onActivityResult
    0.83
    ſelves
    0.80
     itſelf
    0.77
    تقاوى
    0.76
     \\
    0.75
    Activations Density 6.990%

    No Known Activations