© 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. 6620
    Prev
    Next
    INDEX
    Explanations

    text related to categorization or organization

    oai_token-act-pair · gemini-2.0-flash

    instances of categorization or structuring information

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

    division into categories

    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
    __':
    
    -0.75
    __":
    
    -0.73
    aarrggbb
    -0.70
     mxArray
    -0.69
     "");
    
    -0.67
    argout
    -0.67
    "]
    
    -0.66
    '],
    
    -0.66
    Hentet
    -0.65
    __':
    -0.63
    POSITIVE LOGITS
     ویکی‌پدیای
    0.53
     ddelweddau
    0.49
    AddTagHelper
    0.47
    WithIOException
    0.46
     ACCORD
    0.46
     in
    0.44
     adi
    0.44
     Neff
    0.43
     flu
    0.42
     nigga
    0.42
    Activations Density 13.268%

    No Known Activations