© 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. 74501
    Prev
    Next
    INDEX
    Explanations

    available for download or use

    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
    Bi
    0.38
    Rational
    0.38
     Analy
    0.37
     Exhib
    0.37
    liness
    0.36
     Advisory
    0.36
     hashtag
    0.36
    Healthy
    0.36
    न्यास
    0.36
    ਹ
    0.36
    POSITIVE LOGITS
    atae
    0.40
     dacă
    0.38
     pecinta
    0.37
    itares
    0.37
    샘
    0.37
    тур
    0.37
     telefono
    0.36
     генерал
    0.36
     電話
    0.35
    是可以
    0.35
    Activations Density 0.002%

    No Known Activations