© 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. 6409
    Prev
    Next
    INDEX
    Explanations

    adverbs and past tense verbs

    oai_token-act-pair · gemini-2.0-flash

    specific file types and data structures

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

    say "to"

    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
     in
    -0.95
     nella
    -0.73
     on
    -0.69
     trong
    -0.65
     into
    -0.65
     dans
    -0.65
    ใน
    -0.65
     auf
    -0.64
     στον
    -0.59
    在
    -0.59
    POSITIVE LOGITS
     Normdatei
    0.87
    ftagPool
    0.84
    aarrggbb
    0.75
    
    0.73
     Wikispecies
    0.73
    InjectAttribute
    0.69
    AndEndTag
    0.69
     Мексичка
    0.68
    ItemBackground
    0.68
     Bourgoin
    0.66
    Activations Density 2.570%

    No Known Activations