© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4382
    Prev
    Next
    INDEX
    Explanations

    SQL comment clauses

    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_39_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
    दर्
    0.40
    🗾
    0.40
     অ্যান্ট
    0.40
     ஸ்
    0.39
    鈿
    0.39
     derivadas
    0.38
    蚂
    0.38
     revisited
    0.38
    arthed
    0.38
    шал
    0.37
    POSITIVE LOGITS
     <!--
    0.39
     lower
    0.38
     Violation
    0.37
    刺激
    0.37
    Configuration
    0.37
     wear
    0.36
     Lower
    0.35
    lands
    0.35
    下
    0.34
     library
    0.34
    Activations Density 0.005%

    No Known Activations