© 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. 10288
    Prev
    Next
    INDEX
    Explanations

    equations with symbols

    oai_token-act-pair · gemini-2.0-flash

    equals sign

    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
    ValueStyle
    -0.51
    DockStyle
    -0.50
    engager
    -0.46
     ferons
    -0.45
    WriteLiteral
    -0.45
    bibliothek
    -0.44
    {}\
    -0.44
    IActionResult
    -0.44
    colta
    -0.44
    aronder
    -0.43
    POSITIVE LOGITS
     cherchés
    0.76
    WriteTagHelper
    0.65
    PyExc
    0.63
    ineno
    0.63
    oredCriteria
    0.61
     ivelany
    0.59
     Infórmanos
    0.56
     <>",
    0.55
     StatelessWidget
    0.54
    ConstraintMaker
    0.54
    Activations Density 2.694%

    No Known Activations