© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2697
    Prev
    Next
    INDEX
    Explanations

    words expressing strong opinions or feelings

    oai_token-act-pair · gemini-2.0-flash

    maximum

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     CreateTagHelper
    -0.95
     transfieras
    -0.82
     AssemblyCulture
    -0.80
    Hentet
    -0.76
    StoreMessageInfo
    -0.74
     >=",
    -0.67
     viewType
    -0.67
    __(/*!
    -0.66
    httphttps
    -0.66
     चीज़ों
    -0.65
    POSITIVE LOGITS
     maximum
    1.02
    maximum
    0.86
    Maximum
    0.84
     Maximum
    0.75
    最大
    0.73
     max
    0.69
     MAXIMUM
    0.68
    MAXIMUM
    0.66
     maximal
    0.66
    max
    0.64
    Activations Density 2.114%

    No Known Activations