© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 14278
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to familial relationships and some words that follow a forward slash

    oai_token-act-pair · gemini-2.0-flash

    forward slash

    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
     convaincre
    -0.49
     cree
    -0.46
     ISNI
    -0.46
     plumas
    -0.45
     Provinz
    -0.45
    сон
    -0.44
    Gov
    -0.43
    riwal
    -0.42
    uteur
    -0.42
     épais
    -0.42
    POSITIVE LOGITS
     مشين
    0.84
    expandindo
    0.81
    ($__
    0.74
    AddTagHelper
    0.72
    stateMutability
    0.71
     insuffisamment
    0.70
    ArgsConstructor
    0.69
    GenerationType
    0.68
    Tembelea
    0.66
     nakalista
    0.64
    Activations Density 3.615%

    No Known Activations