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. 14449
    Prev
    Next
    INDEX
    Explanations

    the word "to" and helping verbs

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    出版年
    -0.70
     réguli
    -0.70
     âgées
    -0.63
    jekk
    -0.60
     régionale
    -0.58
     supérieures
    -0.58
     gezond
    -0.57
     extérieures
    -0.57
     actualité
    -0.57
     contemporaine
    -0.56
    POSITIVE LOGITS
     فريبيس
    0.91
     مرئيه
    0.57
    BufferException
    0.56
    hObject
    0.55
     nab
    0.52
    yntaxException
    0.49
     CreateTagHelper
    0.48
     put
    0.48
     lash
    0.48
     FishBase
    0.47
    Activations Density 2.983%

    No Known Activations