© 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-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175480
    Prev
    Next
    INDEX
    Explanations

    comparing differences between concepts

    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_24_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
     Argument
    0.36
     त
    0.36
     उनको
    0.35
    gnię
    0.34
     মুহাম্ম
    0.34
    方面的
    0.34
    浏览
    0.33
    .$\
    0.33
     দুপুরে
    0.33
     Indic
    0.33
    POSITIVE LOGITS
     продукти
    0.45
    Duplicate
    0.42
    કિંગ
    0.41
    labeled
    0.40
     actresses
    0.40
     স্নে
    0.40
    docx
    0.40
    Bun
    0.39
    ales
    0.39
    ्ले
    0.39
    Activations Density 0.011%

    No Known Activations