© 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. 14062
    Prev
    Next
    INDEX
    Explanations

    labels for parts of figures in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    dashed lines circles

    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
    :✨
    -0.51
    borderSide
    -0.50
     оригіналу
    -0.50
    Panels
    -0.50
    xtick
    -0.46
    emin
    -0.45
    ertale
    -0.44
     насељу
    -0.44
     poffible
    -0.43
     untere
    -0.43
    POSITIVE LOGITS
    ArgsConstructor
    0.79
     AssemblyCompany
    0.75
     Normdatei
    0.69
    IUrlHelper
    0.63
     BoxDecoration
    0.59
     EconPapers
    0.57
    AndEndTag
    0.56
    webElement
    0.54
     arşivlendi
    0.54
    windowFixed
    0.53
    Activations Density 36.484%

    No Known Activations