© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10648
    Prev
    Next
    INDEX
    Explanations

    computer code and programming terms including struct definitions, assembly language, and package imports

    oai_token-act-pair · gemini-2.0-flash

    wr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    CloseOperation
    -0.81
     Chwiliwch
    -0.73
     صوتيه
    -0.72
    parsedMessage
    -0.71
    хьтан
    -0.70
    IsContent
    -0.69
     Normdatei
    -0.69
     ſtate
    -0.68
     myſelf
    -0.66
    Diwedd
    -0.66
    POSITIVE LOGITS
     v
    0.59
     vàng
    0.59
     WOR
    0.58
     va
    0.58
    avaş
    0.57
     WARE
    0.57
     VIS
    0.56
     WRIT
    0.56
    Verse
    0.56
     Wor
    0.56
    Activations Density 3.467%

    No Known Activations