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. 5845
    Prev
    Next
    INDEX
    Explanations

    baseball player names

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming constructs

    np_token-act-pair-logits · gpt-4o-mini
    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
     thither
    -0.45
     alugar
    -0.44
     intermédiaire
    -0.43
     ivelany
    -0.40
     nomine
    -0.40
     menengah
    -0.40
     Grecs
    -0.38
     oposición
    -0.38
     evening
    -0.37
    ruti
    -0.37
    POSITIVE LOGITS
     betweenstory
    0.98
    StoryboardSegue
    0.95
    DataAnnotations
    0.80
     تضيفلها
    0.77
     OMITBAD
    0.72
     estekak
    0.69
    BufferException
    0.68
    GIVEREF
    0.67
     resourceCulture
    0.65
    andExpect
    0.65
    Activations Density 0.639%

    No Known Activations