© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11007
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and words involved in sending messages and/or Chinese dictonary terms

    oai_token-act-pair · gemini-2.0-flash

    字段

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     a
    -0.60
     
    -0.53
     no
    -0.52
     “
    -0.51
     "
    -0.51
    :
    -0.50
    ,
    -0.47
    ↵↵
    -0.45
     I
    -0.44
     we
    -0.43
    POSITIVE LOGITS
    ſelf
    1.45
     Monfieur
    1.45
     Jefus
    1.38
     itſelf
    1.38
     Reſ
    1.35
     myſelf
    1.34
    存于互联网档案馆
    1.34
    ſelves
    1.33
     ་་
    1.27
     Diſ
    1.26
    Activations Density 1.387%

    No Known Activations