© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1831
    Prev
    Next
    INDEX
    Explanations

    words related to advertising and marketing, plus related app store complaints

    oai_token-act-pair · gemini-2.0-flash

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     EconPapers
    -0.54
    :]:
    -0.54
    DTD
    -0.52
    */].
    -0.51
    })));
    -0.50
    BeginInit
    -0.49
    DebuggerStep
    -0.48
    Letting
    -0.48
    argout
    -0.48
     }}$}
    -0.47
    POSITIVE LOGITS
    OGND
    0.76
    ContentAsync
    0.66
    ftagPool
    0.64
     AssemblyCulture
    0.62
    ISupport
    0.61
     propOrder
    0.59
     оригіналу
    0.58
     []:
    0.57
     initComponents
    0.56
     @"/
    0.55
    Activations Density 0.211%

    No Known Activations