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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7321
    Prev
    Next
    INDEX
    Explanations

    the word "so," and also matches some words ending in "ware" and "such"

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     so
    -3.56
    so
    -1.88
     så
    -1.87
     così
    -1.78
     так
    -1.65
     begitu
    -1.52
     sehingga
    -1.28
     כך
    -1.27
    如此
    -1.23
     niin
    -1.23
    POSITIVE LOGITS
     Diſ
    0.91
     Reſ
    0.91
     ſche
    0.88
     pleaſure
    0.87
     Conſ
    0.84
     houſe
    0.84
     Efq
    0.84
     reaſon
    0.84
     ſtate
    0.84
     whoſe
    0.81
    Activations Density 2.377%

    No Known Activations