Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16284
    Prev
    Next
    INDEX
    Explanations

    code, especially PHP and Python import statements with directory structures

    oai_token-act-pair · gemini-2.0-flash

    software development components

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     plastiques
    -0.58
     Etik
    -0.53
    солю
    -0.52
    Scénario
    -0.51
    :✨
    -0.50
    stdc
    -0.50
     الاطلاع
    -0.49
     للمعارف
    -0.49
     pylint
    -0.49
     HasFactory
    -0.48
    POSITIVE LOGITS
     service
    0.50
    ux
    0.49
    verwijspagina
    0.47
    styleable
    0.45
    }],
    
    0.44
    hline
    0.44
     terça
    0.44
    CrossRef
    0.44
     aastal
    0.44
     WaitForSeconds
    0.43
    Activations Density 0.208%

    No Known Activations