© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7987
    Prev
    Next
    INDEX
    Explanations

    words ending in "a" or relating to enzyme activity

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Мексичка
    -1.09
     дописавши
    -1.00
     useAppContext
    -0.94
     beginnetje
    -0.92
    adaptiveStyles
    -0.91
    ,:);
    -0.88
     Meksiku
    -0.88
    WriteBarrier
    -0.87
    Geplaatst
    -0.86
     FishBase
    -0.86
    POSITIVE LOGITS
    来
    0.28
     средств
    0.26
    re
    0.25
     viata
    0.25
    mimetype
    0.25
     quantités
    0.25
     bonnes
    0.25
    sprechen
    0.25
     administrativos
    0.24
    來
    0.24
    Activations Density 0.312%

    No Known Activations