© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12566
    Prev
    Next
    INDEX
    Explanations

    mentions of paint and painting.

    oai_token-act-pair · gemini-2.0-flash

    paint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     amide
    -0.69
    Viitteet
    -0.69
     scorso
    -0.68
     souten
    -0.67
    EClass
    -0.63
     uș
    -0.63
    fällig
    -0.62
     Janis
    -0.62
     Meso
    -0.61
     albedo
    -0.61
    POSITIVE LOGITS
     a
    0.72
     “
    0.70
     opérateur
    0.65
     головой
    0.62
    AddTagHelper
    0.62
    kuuta
    0.61
     سكانية
    0.61
    ftagPool
    0.61
    PerformLayout
    0.60
    verwijspagina
    0.60
    Activations Density 1.349%

    No Known Activations