© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13389
    Prev
    Next
    INDEX
    Explanations

    code related to Azure Container Registry (ACR)

    oai_token-act-pair · gemini-2.0-flash

    Azure CLI code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    IVEREF
    -0.91
    ьаж
    -0.82
     betweenstory
    -0.75
     Réponses
    -0.71
    évaluateur
    -0.67
    verwijspagina
    -0.65
    Népesség
    -0.61
    Демографія
    -0.61
    MessageTagHelper
    -0.60
     estimés
    -0.60
    POSITIVE LOGITS
     InputDecoration
    0.46
     StatelessWidget
    0.45
    ticularly
    0.43
     spettacolo
    0.40
    (");
    0.38
    DataSnapshot
    0.38
    ærke
    0.38
    avras
    0.38
    ScopeManager
    0.37
    offsetof
    0.36
    Activations Density 3.006%

    No Known Activations