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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16138
    Prev
    Next
    INDEX
    Explanations

    words and prepositions often used in formal or scientific writing, especially in the context of study design, methodology, and results.

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     myſelf
    -1.08
     Jefus
    -0.93
     Majefty
    -0.93
     itſelf
    -0.93
     iſt
    -0.92
     Efq
    -0.91
     ſy
    -0.90
     pleaſure
    -0.89
     houſe
    -0.89
     Anſ
    -0.88
    POSITIVE LOGITS
     the
    0.50
     This
    0.45
     that
    0.44
    SourceChecksum
    0.43
    rasil
    0.42
     this
    0.41
     
    0.41
     my
    0.39
    </h3>
    0.39
     is
    0.38
    Activations Density 3.614%

    No Known Activations