© 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. 7480
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially people's names, and related words like titles.

    oai_token-act-pair · gemini-2.0-flash

    people in articles

    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
     propOrder
    -0.72
     Paglinawan
    -0.66
    webElementXpaths
    -0.62
    Ї
    -0.60
     jsPsych
    -0.59
    ništvo
    -0.58
    UnusedPrivate
    -0.58
    ').
    -0.58
    StructEnd
    -0.57
    ::$_
    -0.56
    POSITIVE LOGITS
     ujednoznacz
    0.52
     istrinya
    0.52
     his
    0.51
    彼は
    0.47
     jScrollPane
    0.47
     متعلقه
    0.45
    Enllaces
    0.44
     виправивши
    0.44
    Handlung
    0.44
    verwijspagina
    0.43
    Activations Density 4.586%

    No Known Activations