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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1585
    Prev
    Next
    INDEX
    Explanations

    code snippets with an emphasis on numbers, special characters, and programming syntax.

    oai_token-act-pair · gemini-2.0-flash

    Code and technical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     myſelf
    -0.58
     coö
    -0.57
     theologians
    -0.55
     themſelves
    -0.55
     itſelf
    -0.54
     canina
    -0.53
     himſelf
    -0.52
     Hymns
    -0.52
     Pathology
    -0.52
     theology
    -0.52
    POSITIVE LOGITS
    )):
    
    0.71
    __':
    
    0.65
    AsUp
    0.65
    #+#
    0.65
    ])):
    0.61
     *)&
    0.60
    ]:
    
    0.58
    featureID
    0.57
    }")
    
    0.57
    ]):
    0.57
    Activations Density 34.502%

    No Known Activations