© 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. 12672
    Prev
    Next
    INDEX
    Explanations

    hedges or tentative statements

    oai_token-act-pair · gemini-2.0-flash

    might or may

    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
     verle
    -0.57
    dora
    -0.57
    rokken
    -0.54
    cellation
    -0.52
    jména
    -0.50
     rall
    -0.49
    Pairing
    -0.48
    arned
    -0.48
    ⓘ
    -0.47
    ები
    -0.47
    POSITIVE LOGITS
    DrawerToggle
    0.72
    ArrowToggle
    0.65
     للمعارف
    0.63
     AssemblyTitle
    0.60
    InjectAttribute
    0.58
    usermodel
    0.58
    jspx
    0.57
    EndProject
    0.57
    tagHelper
    0.57
    reportWebVitals
    0.56
    Activations Density 3.722%

    No Known Activations