© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1377
    Prev
    Next
    INDEX
    Explanations

    mentions of adding a woman to a group or a product being offered

    oai_token-act-pair · gemini-2.0-flash

    Equations and tables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     تضيفلها
    -0.71
     WebDriverWait
    -0.68
     disambiguazione
    -0.67
    )*/
    -0.66
     ujednoznacz
    -0.65
    */;
    -0.64
    ftagPool
    -0.64
     snippetHide
    -0.64
    IUrlHelper
    -0.64
     */;
    -0.63
    POSITIVE LOGITS
     equation
    1.20
     table
    1.09
     mix
    1.08
     picture
    0.86
     Equation
    0.85
    table
    0.84
    equation
    0.84
     Table
    0.82
    Table
    0.82
     equations
    0.79
    Activations Density 0.754%

    No Known Activations