© 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. 48698
    Prev
    Next
    INDEX
    Explanations

    choose or select

    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
    SIZ
    0.37
    黔
    0.34
     aside
    0.34
     Kingdoms
    0.34
    頓
    0.33
     cust
    0.33
    ornado
    0.33
     Galaxies
    0.33
    🙈
    0.33
     Provinces
    0.32
    POSITIVE LOGITS
     whichever
    0.96
     choose
    0.77
    どちら
    0.77
    choose
    0.77
     chooses
    0.76
     pilih
    0.75
    选择
    0.74
     choisir
    0.73
     выбрать
    0.73
     chose
    0.72
    Activations Density 0.107%

    No Known Activations