© 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-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173447
    Prev
    Next
    INDEX
    Explanations

    intensifier followed by positive adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     Stoll
    0.47
     ਸ
    0.42
     বিশ্বাসঘাত
    0.42
    Stuart
    0.42
     Stuart
    0.41
    Davis
    0.41
     थोरो
    0.41
    鮒
    0.40
     स्टी
    0.40
    incontro
    0.40
    POSITIVE LOGITS
     tiny
    0.47
     tini
    0.44
     anime
    0.43
    证券投资基金业协会
    0.42
    janje
    0.42
     duas
    0.42
     ninja
    0.42
     al
    0.41
    ulers
    0.41
     ribu
    0.41
    Activations Density 0.001%

    No Known Activations