© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10314
    Prev
    Next
    INDEX
    Explanations

    instances of the word "paste", plus a few miscellanous false positives.

    oai_token-act-pair · gemini-2.0-flash

    paste

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Connectez
    -0.44
     short
    -0.44
     quinto
    -0.41
     vœ
    -0.41
     maîtres
    -0.39
     second
    -0.38
    kiel
    -0.37
    infeld
    -0.37
     sebaliknya
    -0.36
     vice
    -0.36
    POSITIVE LOGITS
    AddTagHelper
    1.30
    parsedMessage
    1.08
     '\\;'
    0.99
    httphttps
    0.98
     AssemblyCompany
    0.97
     المعيارى
    0.96
    CloseOperation
    0.94
    WriteTagHelper
    0.93
    TintMode
    0.93
    RectangleBorder
    0.91
    Activations Density 1.355%

    No Known Activations