© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15037
    Prev
    Next
    INDEX
    Explanations

    expressions of feelings and opinions

    oai_token-act-pair · gemini-2.0-flash

    laughter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     оригіналу
    -0.86
     Efq
    -0.80
    μως
    -0.78
     ſtill
    -0.75
     Theſe
    -0.75
     uſe
    -0.74
    matchCondition
    -0.72
    ſelf
    -0.71
     iſt
    -0.71
     onOptions
    -0.71
    POSITIVE LOGITS
     ha
    1.09
     Ha
    1.01
    ha
    0.94
    Ha
    0.92
     HA
    0.80
    HA
    0.72
     ;
    0.63
    Hahahahaha
    0.60
     laughs
    0.56
    hem
    0.54
    Activations Density 1.135%

    No Known Activations