© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14326
    Prev
    Next
    INDEX
    Explanations

    fractional numbers, especially those that include "24"

    oai_token-act-pair · gemini-2.0-flash

    24 hours

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     round
    -1.22
     twenty
    -1.10
     
    -1.04
    round
    -1.04
    2
    -1.01
     Round
    -0.98
    Round
    -0.95
     Twenty
    -0.91
     vingt
    -0.86
     TWENTY
    -0.86
    POSITIVE LOGITS
     EconPapers
    0.82
    Datuak
    0.80
    存于互联网档案馆
    0.79
     Fourth
    0.74
    ="@+
    0.70
    Autoritní
    0.69
    featureID
    0.69
     quartet
    0.69
     @"/
    0.68
     فريبيس
    0.68
    Activations Density 0.483%

    No Known Activations