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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11083
    Prev
    Next
    INDEX
    Explanations

    complicated sentences with conjunctions and multiple clauses along with some words with emotional intensity

    oai_token-act-pair · gemini-2.0-flash

    the word 'once'

    np_token-act-pair-logits · gpt-4o-mini

    once

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.85
    angos
    -0.64
    šanai
    -0.63
    ">//
    -0.63
     SIMBAD
    -0.62
     дописавши
    -0.62
     ddelweddau
    -0.59
    .")
    
    -0.59
    ...');
    -0.59
    Eloquent
    -0.58
    POSITIVE LOGITS
     once
    3.83
    once
    3.38
     Once
    3.17
    Once
    3.16
     ONCE
    2.86
    ONCE
    2.66
     einmal
    1.80
     sekali
    1.60
    一旦
    1.49
    一度
    1.48
    Activations Density 3.019%

    No Known Activations