© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16044
    Prev
    Next
    INDEX
    Explanations

    words related to laziness or negative labor practices as well as other negative human qualities.

    oai_token-act-pair · gemini-2.0-flash

    negative opinions of work ethic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     demand
    -0.51
    Demand
    -0.44
     laiton
    -0.44
     Demand
    -0.44
    acı
    -0.43
    Hentet
    -0.43
     ketahui
    -0.42
    setCustom
    -0.42
    ggior
    -0.42
    TabLayout
    -0.42
    POSITIVE LOGITS
    ARROLL
    0.61
     descu
    0.60
     ComVisible
    0.54
    principalTable
    0.54
    spesies
    0.54
     lapsed
    0.53
     tả
    0.52
    HasForeignKey
    0.52
    GTCX
    0.52
     complacency
    0.52
    Activations Density 1.565%

    No Known Activations