© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10305
    Prev
    Next
    INDEX
    Explanations

    angle bracket characters followed by a few specific letters and symbols, which appear to be related to javascript

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Del
    -0.60
    Del
    -0.49
     B
    -0.47
    gin
    -0.46
     
    -0.46
     j
    -0.46
     del
    -0.45
     on
    -0.45
     tem
    -0.45
    ,
    -0.44
    POSITIVE LOGITS
     Мексичка
    1.00
    Personensuche
    0.98
     Efq
    0.98
     myſelf
    0.97
     незавершена
    0.97
     itſelf
    0.97
     trefoil
    0.94
     Shakspeare
    0.94
     doubtnut
    0.93
    хьтан
    0.92
    Activations Density 0.340%

    No Known Activations