© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4275
    Prev
    Next
    INDEX
    Explanations

    words starting with the "des" prefix, sometimes with a slight preference for words related to negative states

    oai_token-act-pair · gemini-2.0-flash

    des

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     مشين
    -0.65
     समीक्षाओं
    -0.63
    setupUi
    -0.59
     desertcart
    -0.55
    存于互联网档案馆
    -0.55
    URLException
    -0.54
    reportWebVitals
    -0.54
    IsPostBack
    -0.54
    DrawerLayout
    -0.52
    MethodManager
    -0.52
    POSITIVE LOGITS
    RegressionTest
    0.75
    SourceChecksum
    0.57
    SequentialGroup
    0.55
    AddHtmlAttribute
    0.54
    ftagPool
    0.52
     Van
    0.47
     Signed
    0.47
    addPreferredGap
    0.46
     whiteColor
    0.46
     archivi
    0.46
    Activations Density 0.418%

    No Known Activations