© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13321
    Prev
    Next
    INDEX
    Explanations

    sections that are important for the overview of an academic paper

    oai_token-act-pair · gemini-2.0-flash

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     resourceCulture
    -0.64
     snippetHide
    -0.60
    RectangleBorder
    -0.56
    verwijspagina
    -0.50
    AddHtmlAttribute
    -0.47
    RenderAtEndOf
    -0.46
     Dür
    -0.46
     <=",
    -0.46
     @"/
    -0.45
    contentLoaded
    -0.45
    POSITIVE LOGITS
     оригіналу
    0.61
     telefónica
    0.59
    ]--;
    0.55
     архивлан
    0.54
     poupée
    0.52
     chrétiens
    0.51
     adjoint
    0.51
    unlimited
    0.50
     ovp
    0.50
     slightest
    0.50
    Activations Density 0.197%

    No Known Activations