© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10785
    Prev
    Next
    INDEX
    Explanations

    code-like syntax

    oai_token-act-pair · gemini-2.0-flash

    Code and math 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
    цезда
    -0.52
     الرياضيه
    -0.51
    ///</
    -0.46
    posedge
    -0.46
    pendenti
    -0.46
    AntiForgeryToken
    -0.45
     ErrIntOverflow
    -0.44
    RuleContext
    -0.43
    CopyWith
    -0.43
    ="@+
    -0.42
    POSITIVE LOGITS
     iconLine
    0.54
    prijs
    0.53
    transQ
    0.52
    UnsafeEnabled
    0.52
    ArrowToggle
    0.51
     ExecuteAsync
    0.48
     članak
    0.47
     RATES
    0.47
    hubung
    0.47
     HasFactory
    0.47
    Activations Density 6.675%

    No Known Activations