© 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. 10110
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of astronomical objects, people, places like "El Dorado Correctional Facility", and bacterial classifications

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns

    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
     
    -0.49
     de
    -0.46
     k
    -0.46
     e
    -0.46
     d
    -0.45
     dan
    -0.44
     Con
    -0.44
     cui
    -0.43
     N
    -0.43
     tu
    -0.43
    POSITIVE LOGITS
     Majefty
    0.79
    存于互联网档案馆
    0.77
     оригіналу
    0.77
     houſe
    0.76
     purpoſe
    0.74
     greateſt
    0.73
     pleaſure
    0.73
     initComponents
    0.73
     שוליים
    0.71
     preſent
    0.71
    Activations Density 4.661%

    No Known Activations