© 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. 5535
    Prev
    Next
    INDEX
    Explanations

    numerical data and labels within tables, statistics, or structured lists

    oai_token-act-pair · gemini-2.0-flash

    numerical digits

    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
     Réponses
    -0.61
    parsedMessage
    -0.59
     zéro
    -0.58
     resté
    -0.56
     gloire
    -0.56
    IUrlHelper
    -0.55
     szabály
    -0.55
     digitais
    -0.55
    ểm
    -0.53
     obligé
    -0.53
    POSITIVE LOGITS
    9
    1.42
    8
    1.19
    7
    1.17
    6
    1.01
    5
    0.89
    4
    0.74
    ۹
    0.71
    ９
    0.67
    ৯
    0.57
    
    0.57
    Activations Density 17.287%

    No Known Activations