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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7003
    Prev
    Next
    INDEX
    Explanations

    uses of the word "now" and verbs in the present perfect tense

    oai_token-act-pair · gemini-2.0-flash

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    now
    -1.18
     now
    -1.03
    Now
    -0.94
     Now
    -0.91
     теперь
    -0.84
     maintenant
    -0.79
     sekarang
    -0.77
     NOW
    -0.76
    ormais
    -0.75
    ahora
    -0.73
    POSITIVE LOGITS
     EconPapers
    0.58
    UnsafeEnabled
    0.56
    ضايا
    0.56
    phazard
    0.55
    afficheront
    0.54
    AddTagHelper
    0.54
    setViewportView
    0.52
    StoryboardSegue
    0.52
     onCancelled
    0.51
    достатки
    0.49
    Activations Density 1.859%

    No Known Activations