© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90206
    Prev
    Next
    INDEX
    Explanations

    code for defining variables

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     соответствующие
    0.37
     altres
    0.36
    otrex
    0.36
    你怎么
    0.35
     Стре
    0.33
     býval
    0.33
     соответствующих
    0.33
    膦
    0.33
     Arce
    0.32
     प्राथमिक
    0.32
    POSITIVE LOGITS
    paying
    0.38
    ɩ
    0.33
     aan
    0.32
    ogram
    0.32
    padding
    0.32
    凊
    0.32
    paid
    0.32
    nv
    0.32
     allowing
    0.31
    rogram
    0.31
    Activations Density 0.046%

    No Known Activations