© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5250
    Prev
    Next
    INDEX
    Explanations

    HTML paragraph tags, anchor tags, and tags in lists, signaling the presence of linked and formatted text

    oai_token-act-pair · gemini-2.0-flash

    non-standard characters or symbols in text

    np_token-act-pair-logits · gpt-4o-mini

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    CppMethod
    -0.96
    CodeAttribute
    -0.68
     InputDecoration
    -0.59
    ngdoc
    -0.59
    cyk
    -0.58
     चीज़ों
    -0.57
     BorderRadius
    -0.57
    __':
    
    -0.56
     AssemblyVersion
    -0.55
    iffion
    -0.54
    POSITIVE LOGITS
     Sélectionnez
    0.57
     OFDb
    0.49
     Türkei
    0.47
     régle
    0.43
     čist
    0.43
    PerformLayout
    0.43
     gomma
    0.41
    chism
    0.41
     negru
    0.40
    calipsis
    0.39
    Activations Density 0.048%

    No Known Activations