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. 14349
    Prev
    Next
    INDEX
    Explanations

    the string "He"

    oai_token-act-pair · gemini-2.0-flash

    he

    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
    :✨
    -0.48
    ри
    -0.41
     Her
    -0.40
     Bu
    -0.40
     évidence
    -0.39
     Water
    -0.39
     Vo
    -0.39
    不得
    -0.38
    fis
    -0.38
    haru
    -0.38
    POSITIVE LOGITS
     Majefty
    0.94
     myſelf
    0.93
     pleaſure
    0.92
     Monfieur
    0.88
     ſeveral
    0.85
     houſe
    0.84
     ſaid
    0.84
     Diſ
    0.81
     fubject
    0.80
     itſelf
    0.80
    Activations Density 0.192%

    No Known Activations