© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4807
    Prev
    Next
    INDEX
    Explanations

    proper nouns and capitalized adjectives

    oai_token-act-pair · gemini-2.0-flash

    words related to a bold city or publication

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

    Products and descriptions

    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
     ExecuteAsync
    -0.79
    CreateModel
    -0.78
    
    -0.77
     createState
    -0.74
    RegistryLite
    -0.73
    yntaxException
    -0.72
     AssemblyTitle
    -0.71
    __':
    -0.69
     autorytatywna
    -0.68
    __":
    -0.68
    POSITIVE LOGITS
    One
    0.47
     veldig
    0.47
     One
    0.46
     financières
    0.46
    Po
    0.46
    <0xD4>
    0.45
     slå
    0.44
     vanskelig
    0.44
    Go
    0.43
    Ca
    0.42
    Activations Density 1.634%

    No Known Activations