© 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. 13422
    Prev
    Next
    INDEX
    Explanations

    parts of machine code, including file names, variables, and function names.

    oai_token-act-pair · 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
    Bibliograf
    -0.57
    ValueStyle
    -0.56
    AsUp
    -0.54
    BASEPATH
    -0.52
    RTGC
    -0.51
    发表于
    -0.51
    webElement
    -0.50
    ullan
    -0.46
    UnitTesting
    -0.46
    ntilde
    -0.44
    POSITIVE LOGITS
    ViewImports
    0.52
     дописавши
    0.48
    
    0.42
    vasti
    0.41
    htdocs
    0.40
     Fort
    0.40
     Sandi
    0.40
     muualla
    0.40
     ModelExpression
    0.40
    oyl
    0.39
    Activations Density 1.660%

    No Known Activations