© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14293
    Prev
    Next
    INDEX
    Explanations

    words relating to the structure and logic of academic papers combined with other seemingly random words

    oai_token-act-pair · gemini-2.0-flash

    Foreign text

    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
    ########.
    -0.56
    mybatisplus
    -0.56
     surla
    -0.51
    essero
    -0.50
    はじめに
    -0.48
    المشاركات
    -0.47
    /***/
    -0.47
    TypedDataSet
    -0.46
     fails
    -0.45
    ValueStyle
    -0.45
    POSITIVE LOGITS
    IsInitialized
    0.66
     RSSSF
    0.64
     Italijanski
    0.60
     marquis
    0.59
     marinho
    0.58
     scoreboard
    0.57
     dafs
    0.56
     scania
    0.56
     terraces
    0.56
     régionale
    0.55
    Activations Density 0.163%

    No Known Activations