© 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. 10480
    Prev
    Next
    INDEX
    Explanations

    words/phrases reflecting uncertainty or qualification

    oai_token-act-pair · gemini-2.0-flash

    Agreement/Uncertainty

    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
     quitted
    -0.62
     Efq
    -0.54
     equipments
    -0.54
    wußt
    -0.52
     egli
    -0.52
     unité
    -0.52
    holdet
    -0.52
     refusé
    -0.51
     medarbe
    -0.51
     matchs
    -0.50
    POSITIVE LOGITS
     оригіналу
    0.80
     ujednoznacz
    0.73
    …~
    0.72
    undrum
    0.72
     noDo
    0.72
    Elsewhere
    0.69
     stumped
    0.69
     digress
    0.68
     Réponses
    0.68
    FWIW
    0.67
    Activations Density 1.368%

    No Known Activations