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. 11034
    Prev
    Next
    INDEX
    Explanations

    the prefix "tele" followed by words related to communication

    oai_token-act-pair · gemini-2.0-flash

    references to telecommunication

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

    tele

    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
     tri
    -0.62
    يديا
    -0.51
    IDENTAL
    -0.49
    createTextNode
    -0.48
     Tri
    -0.48
    ýl
    -0.48
    righ
    -0.47
    мей
    -0.47
    rypt
    -0.47
     Just
    -0.47
    POSITIVE LOGITS
     transfieras
    0.79
    webElementXpaths
    0.76
    GOTREF
    0.72
    ſelves
    0.69
    ſelf
    0.69
     pleaſure
    0.65
    ViewImports
    0.65
     */;
    0.62
    AddTagHelper
    0.60
    IndentedString
    0.60
    Activations Density 0.263%

    No Known Activations