© 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. 221208
    Prev
    Next
    INDEX
    Explanations

    donate to

    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
    Not in Any Lists

    No Comments

    Negative Logits
    買った
    0.37
     bought
    0.37
    買って
    0.35
    Bought
    0.35
    Ordine
    0.35
    買
    0.35
     gé
    0.33
     жовтня
    0.33
    跖
    0.33
    罨
    0.33
    POSITIVE LOGITS
     need
    0.37
    線
    0.36
     crescimento
    0.35
     फैसला
    0.35
     crecimiento
    0.33
     afirm
    0.33
     necessidade
    0.33
     lograr
    0.33
     March
    0.32
     NEED
    0.32
    Activations Density 0.001%

    No Known Activations