© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 12581
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to express gratitude or general well-wishing

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     cappello
    -0.58
     aDecoder
    -0.57
     dénon
    -0.55
     soggior
    -0.53
    kelen
    -0.48
     vectorielles
    -0.48
    atyw
    -0.47
     mattino
    -0.47
     rischio
    -0.47
     suoi
    -0.47
    POSITIVE LOGITS
     оригіналу
    0.81
    تقاوى
    0.70
    发表于
    0.65
    oa̍t
    0.62
    iastes
    0.58
    '}>
    0.57
    ']],
    0.57
    ")));
    
    0.57
     FormGroup
    0.54
    )");
    
    0.54
    Activations Density 0.646%

    No Known Activations