© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11393
    Prev
    Next
    INDEX
    Explanations

    words, phrases and symbols related to customer service, programming errors, IRC, and shame/apologies

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     thank
    -1.50
     sorry
    -1.38
     congratulations
    -1.38
     Thank
    -1.37
    Thank
    -1.33
     apologies
    -1.33
     Sorry
    -1.31
     THANK
    -1.27
    thank
    -1.27
     apology
    -1.20
    POSITIVE LOGITS
     betweenstory
    0.56
    不就是
    0.55
     برانيه
    0.54
    thanes
    0.54
    afficheront
    0.51
     nawr
    0.49
     liné
    0.49
    icals
    0.48
    icity
    0.48
    meaux
    0.48
    Activations Density 1.880%

    No Known Activations