© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33023
    Prev
    Next
    INDEX
    Explanations

    adverb + adjective

    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_7_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
     be
    1.07
     for
    1.00
     pronotum
    0.95
     cheque
    0.93
     peruse
    0.92
     souvenirs
    0.91
    ↵↵
    0.91
     informa
    0.90
     attent
    0.89
     pushbutton
    0.89
    POSITIVE LOGITS
    g
    1.39
    t
    1.38
    ar
    1.23
    ul
    1.20
    ia
    1.09
    os
    1.05
    ان
    1.05
    an
    1.04
    ت
    1.02
    ק
    1.02
    Activations Density 0.001%

    No Known Activations