© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13407
    Prev
    Next
    INDEX
    Explanations

    prepositions and other words that commonly appear in legal documents that identify lawyers or courts

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     للاسماء
    -0.79
     ***!
    -0.69
    bootstrapcdn
    -0.69
    Geplaatst
    -0.66
     Мексичка
    -0.66
    stdc
    -0.65
     BorderRadius
    -0.65
     للمعارف
    -0.64
    ChildScrollView
    -0.63
     propOrder
    -0.62
    POSITIVE LOGITS
     commerciaux
    0.59
    volmente
    0.51
     commerciales
    0.50
     internetowa
    0.49
    ctively
    0.49
     voix
    0.48
    andri
    0.47
    例文
    0.46
     pourraient
    0.45
     referrerpolicy
    0.45
    Activations Density 5.221%

    No Known Activations