© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229647
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and programming constructs

    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_6_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
    a
    1.58
    l
    1.54
    h
    1.53
    is
    1.50
    '
    1.38
    um
    1.33
    ll
    1.31
    ag
    1.27
    de
    1.27
    em
    1.26
    POSITIVE LOGITS
    ון
    1.01
     to
    0.88
     aldehyde
    0.86
    Acetoxy
    0.82
    tLogRow
    0.82
     whiskey
    0.81
    getSupported
    0.79
    SDD
    0.78
     اصحاب
    0.78
     ATTORNEY
    0.78
    Activations Density 0.001%

    No Known Activations