© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127763
    Prev
    Next
    INDEX
    Explanations

    three-dimensional following words

    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_3_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
    1.11
    to
    1.00
    та
    0.98
     to
    0.93
    การ
    0.92
    は
    0.87
     understand
    0.86
    지
    0.85
    :
    0.84
     have
    0.84
    POSITIVE LOGITS
    ни
    1.42
    <0x0D>
    1.06
    نا
    0.98
    و
    0.84
    اني
    0.79
    ل
    0.79
    عود
    0.75
    رد
    0.71
     Cheetah
    0.70
     ника
    0.70
    Activations Density 0.000%

    No Known Activations