© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9508
    Prev
    Next
    INDEX
    Explanations

    code snippets or code-related terms like "swift", "Copyright", "extension", "@available", "public var", "property", "`swift`", "func textField", "UITableView", "class", or "struct".

    oai_token-act-pair · gemini-2.0-flash

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prnewswire
    -0.64
     osallist
    -0.55
     Monfieur
    -0.55
    bootstrapcdn
    -0.54
    VIAF
    -0.52
     myſelf
    -0.52
    ConstraintMaker
    -0.50
     orch
    -0.50
    EDEFAULT
    -0.50
     Ork
    -0.50
    POSITIVE LOGITS
    CROSSTALK
    0.62
    canActivate
    0.60
     surla
    0.59
    CppMethod
    0.57
    reportWebVitals
    0.55
    liminaries
    0.54
    новништво
    0.53
    Bioaccumulative
    0.53
     onBackPressed
    0.51
    webElementXpaths
    0.50
    Activations Density 7.271%

    No Known Activations