© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12320
    Prev
    Next
    INDEX
    Explanations

    technical / academic language

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Italijanski
    -0.59
    ёз
    -0.56
    Prest
    -0.54
     Peque
    -0.52
    TableAdapter
    -0.52
     onResponse
    -0.51
     Appearances
    -0.47
    примеча
    -0.46
    Попис
    -0.46
    gestone
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.73
     Roskov
    0.67
     censiti
    0.56
    ciaio
    0.55
    حوالہ
    0.54
    それと
    0.54
    findpost
    0.53
    المراجع
    0.53
     autorytatywna
    0.52
    مراجع
    0.52
    Activations Density 2.161%

    No Known Activations