© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11437
    Prev
    Next
    INDEX
    Explanations

    words that are important to formal or legal writing, like legal arguments or medical facts.

    oai_token-act-pair · gemini-2.0-flash

    degree or extent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    WriteTagHelper
    -0.60
     réussite
    -0.59
     čaj
    -0.56
    impresa
    -0.56
     médicale
    -0.52
     kullanılan
    -0.51
     financière
    -0.50
     suffices
    -0.49
     The
    -0.49
     convaincre
    -0.49
    POSITIVE LOGITS
    ulipas
    0.68
     BufferedWriter
    0.64
     ISNI
    0.63
    ?}",
    0.62
     /\.
    0.60
    )':
    0.58
    InjectAttribute
    0.58
    Bioaccumulative
    0.57
    complexContent
    0.56
     Мексичка
    0.56
    Activations Density 2.840%

    No Known Activations