© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2599
    Prev
    Next
    INDEX
    Explanations

    anatomical terms and words ending in "ens" and phrases like "and loose group of"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     переписи
    -0.57
    évaluateur
    -0.52
     espor
    -0.50
     ویکی‌پدیا
    -0.49
     radioactivity
    -0.48
    blockList
    -0.47
     činnosti
    -0.45
    üyada
    -0.45
     Roskov
    -0.44
    譲
    -0.43
    POSITIVE LOGITS
     deep
    1.06
     deepest
    1.00
    deep
    0.93
     depth
    0.93
     deeper
    0.90
     deepen
    0.84
     Deeper
    0.82
     deepened
    0.82
     Depth
    0.81
    Deep
    0.80
    Activations Density 0.673%

    No Known Activations