© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4127
    Prev
    Next
    INDEX
    Explanations

    news articles, paying attention to 'the' and 'independent'

    oai_token-act-pair · gemini-2.0-flash

    words starting with '▁'

    np_token-act-pair-logits · gpt-4o-mini

    Nations and politics

    np_max-act-logits · gemini-2.0-flash
    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
    horabuena
    -0.67
    SBATCH
    -0.63
     becauſe
    -0.63
     Dostupné
    -0.63
     Efq
    -0.62
     themſelves
    -0.62
     Tetrahedron
    -0.61
     leſs
    -0.60
     المعيارى
    -0.60
    tellar
    -0.60
    POSITIVE LOGITS
     Ter
    0.54
     sem
    0.52
     semi
    0.52
     Pan
    0.50
    IsMutable
    0.49
     Ma
    0.47
     va
    0.47
     once
    0.46
     Hen
    0.46
     Ho
    0.45
    Activations Density 0.620%

    No Known Activations