© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6519
    Prev
    Next
    INDEX
    Explanations

    mentions of dialogue, especially in the context of communities and organizations

    oai_token-act-pair · gemini-2.0-flash

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    -0.88
     يتيمه
    -0.85
     '\\;'
    -0.84
    ⓧ
    -0.79
    )».
    -0.79
    bootstrapcdn
    -0.79
    ']?>
    -0.79
    enterOuterAlt
    -0.77
    ագրություններ
    -0.77
     kasarigan
    -0.76
    POSITIVE LOGITS
     médié
    0.68
     suprême
    0.64
     laiton
    0.63
     asiatique
    0.61
     chrétien
    0.60
     lumineux
    0.60
     industriel
    0.58
     fourrure
    0.56
     miej
    0.56
     douceur
    0.56
    Activations Density 0.900%

    No Known Activations