© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2217
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a quote

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks or quotations

    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
     Here
    -0.70
    
    -0.69
     ✭✭
    -0.61
     '\\;'
    -0.61
    QWidget
    -0.60
    Here
    -0.60
    těte
    -0.57
    خواندن
    -0.57
     Its
    -0.57
    estacks
    -0.56
    POSITIVE LOGITS
     "
    0.60
     ""
    0.52
     "..
    0.50
     "[
    0.47
     "...
    0.46
     "?
    0.46
     hale
    0.46
     „
    0.45
     “
    0.45
    aspx
    0.44
    Activations Density 1.726%

    No Known Activations