© 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. 4494
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically in the context of the 'acr' command-line tool, possibly related to Azure Container Registry

    oai_token-act-pair · gemini-2.0-flash

    three

    np_max-act-logits · 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
    8
    -0.98
    9
    -0.96
    7
    -0.90
     eight
    -0.76
     Eight
    -0.72
     Eighth
    -0.70
     ninth
    -0.69
     eighth
    -0.69
     EIGHT
    -0.68
    Eight
    -0.68
    POSITIVE LOGITS
     three
    1.19
     ketiga
    1.05
     trois
    1.03
     Three
    1.03
    3
    1.02
     tiga
    0.99
    ３
    0.99
     drei
    0.96
     três
    0.95
     third
    0.94
    Activations Density 2.577%

    No Known Activations