© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9554
    Prev
    Next
    INDEX
    Explanations

    text from an internet chat room, especially French

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    HasForeignKey
    -0.75
    ArgsConstructor
    -0.64
    __(/*!
    -0.60
    脚注の使い方
    -0.57
    esModule
    -0.56
    DoubleQuotes
    -0.53
     subunits
    -0.53
     Egli
    -0.52
     onely
    -0.51
    complexContent
    -0.51
    POSITIVE LOGITS
    kadang
    0.57
     PyLong
    0.56
     dalamnya
    0.52
    PYX
    0.50
    จึง
    0.49
    kunjung
    0.49
    kowania
    0.49
     lo
    0.48
    πάρχ
    0.48
     honte
    0.48
    Activations Density 1.133%

    No Known Activations