© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10924
    Prev
    Next
    INDEX
    Explanations

    abbreviations related to genetics, especially copy number variations

    oai_token-act-pair · gemini-2.0-flash

    CN

    np_max-act · gemini-2.0-flash

    CN

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ogi
    -0.48
    妻
    -0.47
     cliquez
    -0.47
     invasión
    -0.44
    EVT
    -0.44
    frauen
    -0.44
    vacy
    -0.43
    Aire
    -0.43
    utes
    -0.42
    أس
    -0.42
    POSITIVE LOGITS
    BufferException
    0.78
     lenker
    0.78
     Référence
    0.76
     الرياضيه
    0.73
    AutoScaleMode
    0.72
    تقاوى
    0.72
    kháu
    0.69
    VersionUID
    0.66
    脚注の使い方
    0.64
    ();)
    0.63
    Activations Density 1.805%

    No Known Activations