© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5384
    Prev
    Next
    INDEX
    Explanations

    mentions of observatories or climate monitoring programs, especially acronyms and parenthetical abbreviations.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or vocabulary

    np_token-act-pair-logits · gpt-4o-mini

    Scientific data and measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     endwhile
    -0.76
     cherchés
    -0.74
    ">—
    -0.69
     Waray
    -0.68
    AndEndTag
    -0.67
    +#+#
    -0.65
    ,‎
    -0.63
     дописавши
    -0.63
     CURIAM
    -0.62
     initComponents
    -0.61
    POSITIVE LOGITS
     gynhyrchwyd
    0.51
     far
    0.46
    Swap
    0.43
    ValueGeneration
    0.40
     Ju
    0.40
    MinWidth
    0.39
    pher
    0.39
    swap
    0.39
    álló
    0.38
     spit
    0.38
    Activations Density 2.313%

    No Known Activations