© 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. 219741
    Prev
    Next
    INDEX
    Explanations

    ensure AI is aligned

    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
    背包
    0.36
     Calling
    0.36
    نب
    0.36
    ደን
    0.35
    Combat
    0.34
    ท้าย
    0.34
    ไม่ต้อง
    0.33
    ☽
    0.33
    Calling
    0.33
     alerts
    0.33
    POSITIVE LOGITS
     कंग
    0.44
    ռ
    0.42
    uben
    0.39
    いや
    0.38
    鴉
    0.38
     efficacement
    0.37
     эффективно
    0.37
     эффект
    0.37
     negativas
    0.37
    ោះ
    0.37
    Activations Density 0.002%

    No Known Activations