© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6505
    Prev
    Next
    INDEX
    Explanations

    the term "scope" and the framework "Angular."

    oai_token-act-pair · gemini-2.0-flash

    scope

    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
     genoux
    -0.89
     dieux
    -0.87
     armées
    -0.86
     staden
    -0.81
     affari
    -0.81
     alberi
    -0.80
     kysy
    -0.80
     bună
    -0.80
     szob
    -0.79
     tetto
    -0.77
    POSITIVE LOGITS
     bezeichneter
    0.80
    usermodel
    0.77
    expandindo
    0.71
    .*")]
    0.70
     kuli
    0.68
     مشين
    0.66
     obviously
    0.66
     many
    0.65
     visual
    0.65
    tabular
    0.64
    Activations Density 2.995%

    No Known Activations