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. 5982
    Prev
    Next
    INDEX
    Explanations

    descriptions of geographic views

    oai_token-act-pair · gemini-2.0-flash

    views of landscapes or scenery

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

    view

    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
    IndentedString
    -0.82
     lenker
    -0.81
    存于互联网档案馆
    -0.80
     дописавши
    -0.78
     الرياضيه
    -0.78
     Waray
    -0.77
    OGND
    -0.75
     itſelf
    -0.73
     Meksiku
    -0.73
     useAppContext
    -0.73
    POSITIVE LOGITS
     of
    0.50
     al
    0.40
    x
    0.38
     cross
    0.38
     Al
    0.38
    別
    0.38
    ed
    0.37
    p
    0.37
     però
    0.36
    R
    0.36
    Activations Density 5.896%

    No Known Activations