© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10663
    Prev
    Next
    INDEX
    Explanations

    Hungarian names, locations, and educational institutions with their connectives in, from, at, the, and of

    oai_token-act-pair · gemini-2.0-flash

    Random text snippets

    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
    uri
    -0.49
    es
    -0.49
    cheme
    -0.47
    attori
    -0.46
    hes
    -0.45
    鍵
    -0.44
     contri
    -0.44
    nets
    -0.43
    thu
    -0.43
    nen
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.83
     ویکی‌پدی
    0.76
     autorytatywna
    0.74
    argout
    0.73
    sidemargin
    0.71
    MemoryWarning
    0.70
     snippetHide
    0.69
    :✨
    0.69
    Portály
    0.68
     चीज़ों
    0.68
    Activations Density 0.105%

    No Known Activations