© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41705
    Prev
    Next
    INDEX
    Explanations

    chrome web store urls

    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_22_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
    лении
    0.32
     workmanship
    0.32
    ያ
    0.31
     abstain
    0.31
     whimsical
    0.30
    قا
    0.30
    рте
    0.29
    ACES
    0.29
     puffy
    0.29
     Workmen
    0.28
    POSITIVE LOGITS
     सार्वजनिक
    0.32
     अच्छे
    0.31
     édition
    0.30
    啱
    0.29
    rencies
    0.29
    जग
    0.28
     এফ
    0.28
     上海
    0.28
    有机会
    0.27
     resulting
    0.27
    Activations Density 0.001%

    No Known Activations