© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30495
    Prev
    Next
    INDEX
    Explanations

    actions requesting information or assistance

    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_40_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
     Dod
    0.44
     part
    0.38
     ASCII
    0.38
    ृत
    0.38
    volved
    0.37
    thro
    0.37
    (%
    0.37
    part
    0.35
    ('-
    0.35
     `%
    0.35
    POSITIVE LOGITS
    HAL
    0.42
     नेपाली
    0.39
     عطا
    0.36
    やかに
    0.36
    धी
    0.35
    耿
    0.35
     اینڈ
    0.35
     upor
    0.34
    Nepali
    0.34
     HAL
    0.34
    Activations Density 0.006%

    No Known Activations