© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10861
    Prev
    Next
    INDEX
    Explanations

    markup formatting or programming code.

    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
    كويكب
    -0.78
     itſelf
    -0.73
     myſelf
    -0.73
    parsedMessage
    -0.68
     незавершена
    -0.67
     iſt
    -0.67
     faſt
    -0.66
     fût
    -0.66
     démocr
    -0.66
     commerciaux
    -0.65
    POSITIVE LOGITS
    databind
    0.65
    aarrggbb
    0.62
     eventdata
    0.60
    instancetype
    0.59
     servic
    0.57
     geti
    0.56
     fontsize
    0.56
    fre
    0.56
     ph
    0.56
    nameof
    0.54
    Activations Density 3.364%

    No Known Activations