© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3197
    Prev
    Next
    INDEX
    Explanations

    French words and code syntax

    oai_token-act-pair · gemini-2.0-flash

    forum posts/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ADELPHIA
    -0.60
    ntlet
    -0.46
     Exacts
    -0.46
    tinyos
    -0.44
    zten
    -0.43
    celand
    -0.43
    はじめに
    -0.42
    loxy
    -0.42
     past
    -0.41
     leef
    -0.41
    POSITIVE LOGITS
    Hozzáférés
    0.81
     createContext
    0.66
    spesies
    0.66
     venons
    0.64
     createState
    0.62
     Porch
    0.62
    endphp
    0.60
    Région
    0.60
     nhiên
    0.60
     Theſe
    0.60
    Activations Density 5.297%

    No Known Activations