© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13249
    Prev
    Next
    INDEX
    Explanations

    code snippets or quoted text within technical documentation

    oai_token-act-pair · gemini-2.0-flash

    Code/blockquotes

    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
    <bos>
    -0.65
     disambiguazione
    -0.63
     Roskov
    -0.61
     Baillargeon
    -0.61
    windowFixed
    -0.60
     "..\..\
    -0.60
    contentLoaded
    -0.59
    ItemBackground
    -0.58
    >{@
    -0.58
    /*---
    -0.58
    POSITIVE LOGITS
    hyrchwyd
    0.42
    ghijkl
    0.38
    Ap
    0.38
     paradiso
    0.38
    kjø
    0.35
     corde
    0.35
    が欲しい
    0.35
     lenger
    0.34
     livs
    0.34
     ModelExpression
    0.34
    Activations Density 0.296%

    No Known Activations