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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4821
    Prev
    Next
    INDEX
    Explanations

    the word "analysis" and terms close to that word

    oai_token-act-pair · gemini-2.0-flash

    analysis

    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
     analysis
    -2.73
     Analysis
    -2.56
    analysis
    -2.47
    Analysis
    -2.42
     ANALYSIS
    -2.30
     analyses
    -2.13
    分析
    -1.92
    ANALYSIS
    -1.92
     Analyses
    -1.92
     análisis
    -1.91
    POSITIVE LOGITS
     pinulongan
    0.71
    InjectAttribute
    0.69
    InputTagHelper
    0.68
     Réponses
    0.68
    #+#
    0.65
    Rhestr
    0.65
    tonode
    0.65
    ViewImports
    0.63
    CompleteListener
    0.60
    MLLoader
    0.59
    Activations Density 0.468%

    No Known Activations