© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain symbols such as colons, quotes, and operators

    oai_token-act-pair · gemini-2.0-flash

    code symbols

    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
     pinulongan
    -0.91
    Personensuche
    -0.85
    contentLoaded
    -0.80
     CreateTagHelper
    -0.79
    DockStyle
    -0.75
    WriteBarrier
    -0.74
     InputDecoration
    -0.73
     MainAxisSize
    -0.73
     تضيفلها
    -0.71
    writeField
    -0.68
    POSITIVE LOGITS
    igné
    0.52
    ussia
    0.46
    ěstí
    0.46
    docks
    0.44
    ijing
    0.44
    deen
    0.44
     None
    0.43
     пло
    0.42
    ーツ
    0.42
    ansky
    0.42
    Activations Density 1.878%

    No Known Activations