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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16344
    Prev
    Next
    INDEX
    Explanations

    citations (author et al. + venue)

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
    windowFixed
    -0.54
     Normdatei
    -0.52
    principalTable
    -0.52
     pinulongan
    -0.51
     Wicidata
    -0.46
    MethodManager
    -0.46
    StreetMap
    -0.46
    IntentFilter
    -0.46
    InstanceState
    -0.46
    FirebaseDatabase
    -0.45
    POSITIVE LOGITS
     hinweg
    0.63
    
    0.63
     religieuses
    0.56
    cách
    0.53
     nationaux
    0.53
    /*-
    0.52
     viewType
    0.51
    Aiheesta
    0.51
     Sélection
    0.50
     Сайт
    0.50
    Activations Density 1.513%

    No Known Activations