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. 11135
    Prev
    Next
    INDEX
    Explanations

    code syntax, particularly relating to importing and exporting modules

    oai_token-act-pair · gemini-2.0-flash

    code-related keywords

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

    Code-related

    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
     endforeach
    -0.59
    fastjson
    -0.58
    KEYCODE
    -0.56
    IBOutlet
    -0.55
    sidemargin
    -0.54
    Hochspringen
    -0.52
    orElseThrow
    -0.52
    databind
    -0.51
     noqa
    -0.51
    fromCharCode
    -0.50
    POSITIVE LOGITS
    曖昧さ回避
    0.53
     Autorizaciones
    0.52
     Importing
    0.51
    깥
    0.50
    Importing
    0.49
     importing
    0.48
     tiefer
    0.48
     aidant
    0.47
     cucchia
    0.47
    Бахар
    0.47
    Activations Density 0.887%

    No Known Activations