© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129563
    Prev
    Next
    INDEX
    Explanations

    sounds like words ending in -itter, -uffle, -inge, -ives, -falls, -dle, -ise

    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
    e
    1.13
    ك
    0.96
     dupla
    0.92
     وړیا
    0.89
     memoria
    0.88
    i
    0.88
    ↵
    0.84
    ið
    0.83
     genética
    0.83
     vadati
    0.83
    POSITIVE LOGITS
     It
    1.19
     to
    1.11
    س
    1.05
     There
    0.94
    to
    0.92
    0
    0.91
    ik
    0.90
    I
    0.88
    V
    0.88
    ص
    0.88
    Activations Density 0.007%

    No Known Activations