© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193426
    Prev
    Next
    INDEX
    Explanations

    categories of tasks or concepts

    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_27_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
    Ꮏ
    0.41
    ଢ
    0.40
     bara
    0.40
    ிலை
    0.38
    illary
    0.37
    ijal
    0.36
     sheet
    0.36
     haar
    0.35
    angement
    0.35
     பூஜை
    0.35
    POSITIVE LOGITS
     स
    0.39
    모
    0.38
     अक्सर
    0.37
     항상
    0.37
     不能
    0.37
     often
    0.36
     organismos
    0.36
     따르면
    0.35
     cdot
    0.35
     दब
    0.34
    Activations Density 0.007%

    No Known Activations