© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9767
    Prev
    Next
    INDEX
    Explanations

    paste or glue

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ʳ
    0.75
     이때
    0.70
     इजीली
    0.69
     ఏర్
    0.67
     entwickeln
    0.67
     Repeat
    0.67
     Repeating
    0.65
    [-
    0.65
    )[
    0.65
     mf
    0.64
    POSITIVE LOGITS
    paste
    1.47
     paste
    1.47
     Paste
    1.12
     glue
    1.09
     pastes
    1.03
    glue
    1.00
     adhesive
    0.94
     pasting
    0.91
    粘贴
    0.88
    table
    0.86
    Activations Density 0.084%

    No Known Activations