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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5594
    Prev
    Next
    INDEX
    Explanations

    terms relating to literature and writing, especially when used in an academic context

    oai_token-act-pair · gemini-2.0-flash

    Verse

    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
     literary
    -1.08
    Literature
    -0.98
     Literary
    -0.98
     Literature
    -0.94
     liter
    -0.91
    literary
    -0.91
    Literary
    -0.90
     literature
    -0.90
     LITERATURE
    -0.80
    literature
    -0.80
    POSITIVE LOGITS
     verse
    0.87
    Verse
    0.75
    verse
    0.73
    __(/*!
    0.73
     Verse
    0.68
    تقاوى
    0.65
    verses
    0.63
     verso
    0.63
     verses
    0.59
    ⓧ
    0.54
    Activations Density 2.763%

    No Known Activations