© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257119
    Prev
    Next
    INDEX
    Explanations

    What questions

    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_22_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
     ዘዴ
    0.48
     Г
    0.46
     Coolidge
    0.43
     SPEED
    0.41
    organizzazione
    0.40
     ouvertes
    0.40
    鷸
    0.40
     exped
    0.39
     ouvert
    0.39
     fotografie
    0.38
    POSITIVE LOGITS
     तया
    0.39
    hookrightarrow
    0.38
    要
    0.38
     creatives
    0.37
    昉
    0.36
    يزة
    0.36
     പിന്നെ
    0.35
    另
    0.35
    FAF
    0.34
    pronounced
    0.34
    Activations Density 0.006%

    No Known Activations