© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8768
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, quotes, and interjections, especially those expressing excitement or conclusion.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    A
    -0.47
    Становништво
    -0.45
    衛門
    -0.44
    ArgsConstructor
    -0.42
     wow
    -0.40
     qed
    -0.40
     Denne
    -0.39
     coolest
    -0.39
     Arrangements
    -0.39
     LoginComponent
    -0.39
    POSITIVE LOGITS
    
    0.87
     snippetHide
    0.84
    principalTable
    0.75
    MemoryWarning
    0.71
    FormTagHelper
    0.69
    MessageOf
    0.68
     onCreateView
    0.66
     ویکی‌پدیا
    0.65
    انيف
    0.63
    :✨
    0.62
    Activations Density 2.156%

    No Known Activations