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. 11103
    Prev
    Next
    INDEX
    Explanations

    words related to systems and processes in various domains like computing, finance, biology, and management/leadership.

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or specific terms in various contexts

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

    Systems

    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
    .
    -0.62
    ,
    -0.54
     bahwa
    -0.38
     when
    -0.38
     
    -0.38
     after
    -0.38
     setelah
    -0.38
    <eos>
    -0.38
     apapun
    -0.38
     and
    -0.37
    POSITIVE LOGITS
     متعلقه
    1.14
    rungsseite
    1.06
    ]--;
    1.05
     onPostExecute
    0.91
     незавершена
    0.91
    CodedInputStream
    0.90
    expandindo
    0.90
     attends
    0.90
    twimg
    0.90
    )++;
    0.89
    Activations Density 7.192%

    No Known Activations