© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15492
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to scientific assays, studies and results

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     présents
    -0.67
     courants
    -0.64
     esprits
    -0.63
     fidèles
    -0.62
     présent
    -0.62
     deseos
    -0.60
     pauvres
    -0.60
     brazos
    -0.60
     côtés
    -0.60
     faciles
    -0.59
    POSITIVE LOGITS
     doubtnut
    0.93
     Efq
    0.87
     photolibrary
    0.87
     myſelf
    0.86
     ་་
    0.82
     itſelf
    0.80
     raiſ
    0.80
     ―――――
    0.79
     Pliocene
    0.79
     cwt
    0.79
    Activations Density 14.930%

    No Known Activations