© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3957
    Prev
    Next
    INDEX
    Explanations

    words ending in "ization" or containing "ize"

    oai_token-act-pair · gemini-2.0-flash

    ization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     päivä
    -0.67
     måte
    -0.63
     henkil
    -0.62
     oike
    -0.62
     umane
    -0.62
     farba
    -0.61
     määrä
    -0.60
     individuale
    -0.58
     sjuk
    -0.57
     sportowe
    -0.57
    POSITIVE LOGITS
    parsedMessage
    1.24
    complexContent
    1.21
    tagHelperRunner
    1.17
    awtextra
    1.09
    RegistryLite
    1.06
     surla
    1.06
    LookAnd
    1.05
    abestanden
    1.03
    "):
    1.02
     NSCoder
    1.02
    Activations Density 0.928%

    No Known Activations