Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10000
    Prev
    Next
    INDEX
    Explanations

    descriptive language about novels and literature

    oai_token-act-pair · gemini-2.0-flash

    fiction genres

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     esternos
    -0.57
    وصلات
    -0.53
     estimés
    -0.52
     telefónica
    -0.50
    HIRE
    -0.49
     calciatore
    -0.49
    ulin
    -0.47
    Identyfik
    -0.47
    cita
    -0.47
     berta
    -0.47
    POSITIVE LOGITS
     fiction
    0.93
     fantasy
    0.79
     novels
    0.74
    setVerticalGroup
    0.72
     nonfiction
    0.70
     mystery
    0.68
     thriller
    0.68
     Fiction
    0.67
    Fiction
    0.66
     fictional
    0.65
    Activations Density 1.417%

    No Known Activations