© 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. 5427
    Prev
    Next
    INDEX
    Explanations

    technical articles on power supplies and the use of hydrogen peroxide

    oai_token-act-pair · gemini-2.0-flash

    electrical loads

    np_max-act-logits · gemini-2.0-flash
    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
    polazione
    -0.59
    chromedriver
    -0.58
     protoimpl
    -0.57
    pédie
    -0.55
     defStyle
    -0.54
    და
    -0.52
     UnityEditor
    -0.52
     Infórmanos
    -0.52
    Nath
    -0.51
     JpaRepository
    -0.51
    POSITIVE LOGITS
     draw
    0.71
     draws
    0.63
     power
    0.60
     loads
    0.60
     load
    0.60
     drew
    0.58
    load
    0.57
    Draws
    0.57
    draw
    0.57
     drawn
    0.57
    Activations Density 3.632%

    No Known Activations