© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11138
    Prev
    Next
    INDEX
    Explanations

    words that can be used to describe something that involves a degree of scientific or complex reasoning.

    oai_token-act-pair · 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
    ity
    -1.54
    al
    -1.45
    ally
    -1.09
    ITY
    -0.97
    ly
    -0.91
    ually
    -0.90
    ALLY
    -0.88
    ingly
    -0.87
    ️
    -0.86
    ishly
    -0.83
    POSITIVE LOGITS
    Autoritní
    0.49
    Espèce
    0.48
    awin
    0.44
    cumin
    0.44
     propOrder
    0.43
     كومونز
    0.41
     سكانية
    0.40
    віч
    0.40
     InputDecoration
    0.40
     Sa
    0.40
    Activations Density 2.764%

    No Known Activations