© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194695
    Prev
    Next
    INDEX
    Explanations

    QGIS

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ത
    0.47
     punctuation
    0.40
     યુ
    0.39
    亮
    0.38
     Eileen
    0.38
     svc
    0.38
     கி
    0.37
     Bia
    0.37
    光源
    0.36
    hores
    0.36
    POSITIVE LOGITS
    enders
    0.42
    㛺
    0.42
    ୬
    0.41
    geri
    0.41
    ăng
    0.40
    icosa
    0.40
    CR
    0.38
     wary
    0.38
     Jair
    0.37
    嘣
    0.37
    Activations Density 0.001%

    No Known Activations