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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12190
    Prev
    Next
    INDEX
    Explanations

    a variety of items in academic papers, sometimes related to numbers and measurements.

    oai_token-act-pair · gemini-2.0-flash

    sentence endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ValueStyle
    -0.77
    fjspx
    -0.72
    PerformLayout
    -0.72
     nakalista
    -0.65
     disponibilités
    -0.65
    StructEnd
    -0.61
     GenerationType
    -0.60
    InputBorder
    -0.59
    脚注の使い方
    -0.58
    Revenir
    -0.57
    POSITIVE LOGITS
    Населення
    0.55
    σουμε
    0.52
    ритори
    0.51
     Prior
    0.49
    ethene
    0.48
    ↵↵
    0.48
     '?'
    0.47
     Taschen
    0.47
     Olímpicos
    0.47
     phosphoric
    0.46
    Activations Density 0.989%

    No Known Activations