© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13638
    Prev
    Next
    INDEX
    Explanations

    words that connect logical ideas in an argument, or are prepositions.

    oai_token-act-pair · gemini-2.0-flash

    algorithms and feature selection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyProduct
    -0.69
    Enllaces
    -0.67
    Билгалдахарш
    -0.62
     Italijanski
    -0.62
    programs
    -0.57
     betweenstory
    -0.57
    program
    -0.56
     Económica
    -0.56
     MutableLiveData
    -0.56
     programs
    -0.56
    POSITIVE LOGITS
    BarStyle
    0.52
    żeli
    0.51
     isInitialized
    0.45
    יוחד
    0.45
    IsContent
    0.44
     Crosse
    0.44
     She
    0.43
    acons
    0.43
     contr
    0.42
    uffe
    0.42
    Activations Density 4.181%

    No Known Activations