© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31267
    Prev
    Next
    INDEX
    Explanations

    return statement

    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_31_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
     pit
    0.36
     pits
    0.35
     Boley
    0.34
    熱
    0.34
    定位
    0.34
    दाश्त
    0.34
     Fulton
    0.33
     industries
    0.33
     lao
    0.33
     переписи
    0.33
    POSITIVE LOGITS
     departure
    0.52
     Departure
    0.52
    Departure
    0.51
     выход
    0.48
    帰
    0.45
     dismissal
    0.43
     exit
    0.43
     transportation
    0.43
     departures
    0.41
    帰り
    0.40
    Activations Density 0.077%

    No Known Activations