© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11564
    Prev
    Next
    INDEX
    Explanations

    financial terms, computer terms related to internet, references to voting and political actions as well as references to scientific formulas/papers.

    oai_token-act-pair · gemini-2.0-flash

    net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    存于互联网档案馆
    -0.81
    PerformLayout
    -0.77
    AddTagHelper
    -0.71
     recognising
    -0.70
    uests
    -0.70
    Externé
    -0.69
    WriteBarrier
    -0.69
     Dames
    -0.66
    pportun
    -0.66
    ratulations
    -0.66
    POSITIVE LOGITS
     colorés
    0.68
     réglable
    0.68
     titolata
    0.67
     conçus
    0.65
     verrez
    0.65
     journalistes
    0.65
     présidenti
    0.64
     aéri
    0.64
     rosse
    0.63
     noires
    0.63
    Activations Density 2.065%

    No Known Activations