© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12972
    Prev
    Next
    INDEX
    Explanations

    a variety of legal and clothing related terms.

    oai_token-act-pair · gemini-2.0-flash

    legal text and clothing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Билгалдахарш
    -0.88
    WriteTagHelper
    -0.84
    AddTagHelper
    -0.79
     itſelf
    -0.78
    Viitteet
    -0.77
     CreateTagHelper
    -0.74
     Spisak
    -0.73
     pleaſure
    -0.69
     JpaRepository
    -0.69
    #+#
    -0.69
    POSITIVE LOGITS
    ArrowToggle
    0.51
     tredje
    0.44
     års
    0.39
    WriteAttribute
    0.39
    prime
    0.39
     aceste
    0.38
    AddHtmlAttribute
    0.37
    ParallelGroup
    0.37
     Soft
    0.37
    Ễ
    0.36
    Activations Density 1.191%

    No Known Activations