© 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. 30218
    Prev
    Next
    INDEX
    Explanations

    numbers, spelling, literacy

    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
    Negative Logits
     जात
    0.39
    Makeup
    0.37
     teenage
    0.36
     auspices
    0.36
     teenagers
    0.35
     ethics
    0.35
     landscape
    0.35
    zeichnung
    0.34
    헹
    0.34
    Landscape
    0.34
    POSITIVE LOGITS
     Spelling
    0.47
    மி
    0.47
     Curriculum
    0.45
    Pup
    0.41
     Kindergarten
    0.41
     Classroom
    0.40
     Literacy
    0.39
     Vocabulary
    0.39
     hứng
    0.39
     phon
    0.39
    Activations Density 0.000%

    No Known Activations