© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81029
    Prev
    Next
    INDEX
    Explanations

    represent knowledge or relationships

    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_29_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
     නිර්
    0.47
    ⁱ
    0.42
     смер
    0.41
     unifying
    0.39
     नित
    0.39
    ための
    0.38
     moisturizing
    0.38
     കഴിഞ്ഞ
    0.37
     નિર્
    0.37
     ไล
    0.37
    POSITIVE LOGITS
    \
    0.37
    egas
    0.36
     beob
    0.36
    ibor
    0.36
     oleh
    0.35
     observaciones
    0.35
     observations
    0.35
    enez
    0.35
    how
    0.35
    owels
    0.35
    Activations Density 0.015%

    No Known Activations