© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11371
    Prev
    Next
    INDEX
    Explanations

    periods at the end of sentences and paragraph breaks in a script

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     propOrder
    -0.74
    TagMode
    -0.58
    BeginInit
    -0.57
     ligiloj
    -0.57
     BoxFit
    -0.54
    ServletException
    -0.54
    sqcup
    -0.52
    IBOutlet
    -0.51
    protoc
    -0.50
    EndInit
    -0.50
    POSITIVE LOGITS
     erscheinen
    0.53
    Soto
    0.51
    toft
    0.49
     getchar
    0.48
    ļu
    0.48
    がって
    0.46
    Come
    0.46
    kým
    0.46
    transQ
    0.45
    riwal
    0.45
    Activations Density 0.397%

    No Known Activations