© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3003
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies of antibacterial effects of organic molecules.

    oai_token-act-pair · gemini-2.0-flash

    specific types of herbal extracts and oils

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

    medicine

    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
     Extragalactic
    -0.73
    Datuak
    -0.65
    ]--;
    -0.65
    <?
    -0.63
    httphttps
    -0.63
     defaultstate
    -0.62
    WithMany
    -0.61
    tonode
    -0.61
     kasarigan
    -0.60
     LoggerFactory
    -0.60
    POSITIVE LOGITS
     الاطلاع
    0.48
     Co
    0.47
    mint
    0.44
    ిక
    0.44
     patch
    0.44
    Patch
    0.43
     Patch
    0.42
     Men
    0.42
     Pokies
    0.41
    ähig
    0.41
    Activations Density 1.047%

    No Known Activations