© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15773
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions

    oai_token-act-pair · gemini-2.0-flash

    relating to 100

    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
     виправивши
    -1.10
    تقاوى
    -0.94
    脚注の使い方
    -0.87
     protoimpl
    -0.85
     EconPapers
    -0.83
     MainAxisSize
    -0.80
     صوتيه
    -0.76
    DoubleQuotes
    -0.75
     فريبيس
    -0.74
    存于互联网档案馆
    -0.71
    POSITIVE LOGITS
     hundred
    1.17
    hundred
    1.10
     Hundred
    0.98
    Hundred
    0.94
     cent
    0.92
     hundert
    0.78
     half
    0.76
     HUND
    0.75
     fifty
    0.73
    half
    0.68
    Activations Density 1.628%

    No Known Activations