© 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. 15662
    Prev
    Next
    INDEX
    Explanations

    the phrase "a great deal".

    oai_token-act-pair · gemini-2.0-flash

    deal

    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
    omiast
    -0.64
     immemorial
    -0.59
     honours
    -0.59
     honour
    -0.56
     Visser
    -0.54
     imp
    -0.52
     Honours
    -0.51
     honoured
    -0.50
     organised
    -0.50
     favours
    -0.50
    POSITIVE LOGITS
    :✨
    0.98
     GenerationType
    0.88
    NameInMap
    0.82
     vPvB
    0.77
    Rüyada
    0.75
    wpi
    0.74
    $_['
    0.73
    unknownFields
    0.73
    ttemberg
    0.73
    webElementXpaths
    0.73
    Activations Density 0.200%

    No Known Activations