© 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. 14935
    Prev
    Next
    INDEX
    Explanations

    words associated with books and authors

    oai_token-act-pair · gemini-2.0-flash

    About writers and fiction

    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
     authors
    -1.59
     Writers
    -1.54
     writers
    -1.53
     writer
    -1.52
     author
    -1.51
    Writers
    -1.48
     Writer
    -1.47
     Authors
    -1.46
    writer
    -1.39
    Author
    -1.37
    POSITIVE LOGITS
    LayoutConstraint
    0.69
    iformis
    0.55
     defaultstate
    0.55
     sī
    0.54
     وتسجيلات
    0.50
    ionView
    0.49
    kset
    0.49
    stateMutability
    0.47
     Barbier
    0.46
    തി
    0.46
    Activations Density 5.804%

    No Known Activations