© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96443
    Prev
    Next
    INDEX
    Explanations

    viruses and molecules

    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_14_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
    {
    0.20
    }
    0.18
    _
    0.18
    (
    0.18
    การ
    0.17
     การ
    0.16
    0.16
     index
    0.16
    ว
    0.15
    B
    0.15
    POSITIVE LOGITS
    లా
    0.18
     Фургала
    0.18
    ﺯ
    0.17
    helpTool
    0.17
     Paise
    0.17
    INTa
    0.17
    雹
    0.17
     ސ
    0.17
     Стаўкі
    0.17
     ಹೀ
    0.17
    Activations Density 0.014%

    No Known Activations