© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15134
    Prev
    Next
    INDEX
    Explanations

    code snippets and mathematical expressions, especially focusing on gnuplot tasks and ratios

    oai_token-act-pair · gemini-2.0-flash

    Code and equations

    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
     AppCompatTheme
    -0.64
     HttpNotFound
    -0.56
    ########.
    -0.55
    kovic
    -0.54
     Italijanski
    -0.53
    PLANATION
    -0.52
    ugar
    -0.51
     تانيه
    -0.51
    STILL
    -0.50
    verages
    -0.50
    POSITIVE LOGITS
    IsContent
    0.69
    GenerationType
    0.59
    ScopeManager
    0.51
     Hopf
    0.49
     تضيفلها
    0.48
    endregion
    0.46
    mergeFrom
    0.46
    migrationBuilder
    0.46
     kasarigan
    0.45
    SequentialGroup
    0.45
    Activations Density 0.363%

    No Known Activations