© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221242
    Prev
    Next
    INDEX
    Explanations

    not a medical professional

    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
    Negative Logits
    руса
    0.42
    thon
    0.38
     Sovereign
    0.36
    Rak
    0.36
    Ampl
    0.36
     დაი
    0.36
    不由
    0.35
    作者
    0.35
     নুর
    0.35
    煽
    0.35
    POSITIVE LOGITS
     जातात
    0.35
    භ
    0.34
     থাকলেও
    0.33
     প্রচলিত
    0.33
    发的
    0.32
     उपयोग
    0.32
     spinners
    0.32
     reals
    0.32
    这条
    0.31
     spinner
    0.31
    Activations Density 0.011%

    No Known Activations