© 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. 13810
    Prev
    Next
    INDEX
    Explanations

    uppercase acronyms including "H"

    oai_token-act-pair · gemini-2.0-flash

    terms related to biochemical measurements

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

    H

    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
     isSet
    -0.61
    OHN
    -0.56
    Rujuakan
    -0.50
    zet
    -0.49
    zerű
    -0.48
     Multi
    -0.45
    Geplaatst
    -0.45
    eraus
    -0.45
     Sure
    -0.43
    typical
    -0.43
    POSITIVE LOGITS
    Personendaten
    0.71
    AndEndTag
    0.68
     ویکی‌پدیای
    0.63
    makeText
    0.61
    Искәрмәләр
    0.61
    Rhestr
    0.59
    ArrowToggle
    0.57
    WindowConstants
    0.57
    GenerationType
    0.57
     Signalez
    0.57
    Activations Density 0.948%

    No Known Activations