© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7720
    Prev
    Next
    INDEX
    Explanations

    words and phrases about rules, agreements, or guidelines

    oai_token-act-pair · gemini-2.0-flash

    location or spatial relation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ISNI
    -0.70
     سكانية
    -0.66
    elemField
    -0.65
     laikā
    -0.64
    thâu
    -0.63
     kysy
    -0.61
     päivä
    -0.61
    Datuak
    -0.61
     betweenstory
    -0.61
    utveck
    -0.60
    POSITIVE LOGITS
     Their
    0.83
     Through
    0.81
     Within
    0.80
     Again
    0.79
     Between
    0.76
     Besides
    0.76
     Without
    0.76
     Throughout
    0.75
     In
    0.75
     They
    0.75
    Activations Density 42.794%

    No Known Activations