© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10576
    Prev
    Next
    INDEX
    Explanations

    tokens in documents related to finance, location names, history or burial grounds

    oai_token-act-pair · gemini-2.0-flash

    Memorials

    np_max-act-logits · gemini-2.0-flash
    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
    StoryboardSegue
    -0.87
    rungsseite
    -0.85
     تضيفلها
    -0.82
    참고
    -0.82
    Vidite
    -0.81
    DockStyle
    -0.81
     himo
    -0.80
    تقاوى
    -0.76
     nakalista
    -0.76
     resourceCulture
    -0.75
    POSITIVE LOGITS
     Chapel
    0.48
     chapel
    0.43
    BETWEEN
    0.39
    יר
    0.38
     Directors
    0.38
     Dire
    0.38
     tucked
    0.38
    Chapel
    0.37
     placé
    0.37
     Keluarga
    0.36
    Activations Density 0.927%

    No Known Activations