© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235598
    Prev
    Next
    INDEX
    Explanations

    remember to V

    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_25_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
     önemlidir
    0.36
    Recognition
    0.31
     fundamentales
    0.31
    rokken
    0.31
    <unused69>
    0.31
     కీల
    0.30
     hunted
    0.30
     soared
    0.30
     الحالي
    0.30
    <unused494>
    0.29
    POSITIVE LOGITS
     PLUS
    0.35
     beyond
    0.35
     LOVE
    0.34
     Με
    0.34
     Ve
    0.33
    δ
    0.33
     Pi
    0.32
    无论
    0.32
     χωρίς
    0.32
    Με
    0.32
    Activations Density 0.001%

    No Known Activations