© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5386
    Prev
    Next
    INDEX
    Explanations

    words related to measurement and science

    oai_token-act-pair · gemini-2.0-flash

    energy

    np_max-act-logits · gemini-2.0-flash

    foreign scripts

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    s
    -0.43
     
    -0.35
    ft
    -0.32
    fer
    -0.30
    e
    -0.29
     Шта
    -0.29
    E
    -0.29
    R
    -0.26
     fede
    -0.26
    Common
    -0.26
    POSITIVE LOGITS
     كومونز
    1.22
     Мексичка
    1.16
    InjectAttribute
    1.11
     الحره
    1.11
     '\\;'
    1.05
    adaptiveStyles
    1.04
    :✨
    1.03
    Hentet
    1.02
    Hochspringen
    1.02
    
    1.02
    Activations Density 29.409%

    No Known Activations