© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102992
    Prev
    Next
    INDEX
    Explanations

    dress

    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_14_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
    Chu
    0.58
    つけ
    0.55
    \}$.
    0.53
    Customers
    0.52
    CustomerID
    0.52
    Sept
    0.51
    ቒ
    0.51
    CNC
    0.50
     groundwork
    0.50
    גי
    0.50
    POSITIVE LOGITS
     Infantil
    0.64
    থর
    0.62
     É
    0.57
    ários
    0.54
     Þ
    0.54
    anjutnya
    0.53
    ndal
    0.53
     voulait
    0.52
     Filho
    0.52
    uminium
    0.52
    Activations Density 0.003%

    No Known Activations