© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 14993
    Prev
    Next
    INDEX
    Explanations

    code and programming terms

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     y
    -0.45
     nose
    -0.45
     mind
    -0.44
    Front
    -0.43
    甸
    -0.43
     front
    -0.42
    entif
    -0.42
    ÁB
    -0.41
     head
    -0.41
    oure
    -0.41
    POSITIVE LOGITS
    Vidite
    0.82
    HtmlAttribute
    0.80
     चीज़ों
    0.79
     دیکھیے
    0.75
    GraphicsUnit
    0.75
    GenerationType
    0.74
     snippetHide
    0.74
     /\.
    0.73
    "):
    0.69
    WriteBarrier
    0.69
    Activations Density 2.675%

    No Known Activations