© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18929
    Prev
    Next
    INDEX
    Explanations

    sql keywords, data types, and functions

    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
     vacuum
    0.39
    ℚ
    0.38
    apanam
    0.37
     świat
    0.37
     Vacuum
    0.36
    aurants
    0.35
     Heather
    0.35
     buss
    0.35
     vac
    0.35
    Vacuum
    0.35
    POSITIVE LOGITS
     Pl
    0.42
    㖪
    0.41
    Donna
    0.40
     Composite
    0.39
    ">';
    0.38
     Stability
    0.38
     '*':
    0.37
     Tzu
    0.37
     आवृत्ति
    0.37
    鄀
    0.37
    Activations Density 0.018%

    No Known Activations