© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11869
    Prev
    Next
    INDEX
    Explanations

    words related to creating written material

    oai_token-act-pair · gemini-2.0-flash

    books and related media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     book
    -1.02
    Книга
    -0.93
    book
    -0.85
    Book
    -0.84
    BOOK
    -0.78
     Book
    -0.75
     BoxDecoration
    -0.74
     BOOK
    -0.72
     novel
    -0.69
     libro
    -0.65
    POSITIVE LOGITS
    ftagPool
    0.52
     table
    0.52
    րջ
    0.51
     SearchView
    0.50
    Географиясе
    0.50
    ében
    0.49
     kohdetta
    0.49
    väg
    0.48
    ArrowToggle
    0.48
     otomatig
    0.47
    Activations Density 4.858%

    No Known Activations