© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14666
    Prev
    Next
    INDEX
    Explanations

    references to numbered concepts, centuries, and legal terminology

    oai_token-act-pair · gemini-2.0-flash

    U

    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
     cref
    -0.64
    4
    -0.63
    5
    -0.61
    sette
    -0.57
     sabre
    -0.56
    derdag
    -0.54
     Sabre
    -0.53
    ecken
    -0.53
     Öz
    -0.52
    chman
    -0.51
    POSITIVE LOGITS
    errHandler
    0.76
    XXI
    0.72
     NSString
    0.72
     XXI
    0.71
     Lombardi
    0.71
    Хьажоргаш
    0.69
    rinth
    0.68
    RTLD
    0.67
    Trama
    0.66
    aliyun
    0.66
    Activations Density 8.041%

    No Known Activations