© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24871
    Prev
    Next
    INDEX
    Explanations

    Mixed languages and numbers

    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_56_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
    แ
    1.31
     praises
    0.73
     refined
    0.68
    Pra
    0.64
    awards
    0.64
    industry
    0.63
     awards
    0.63
     referred
    0.62
     industry
    0.62
    Refer
    0.61
    POSITIVE LOGITS
     пользу
    0.39
    чний
    0.38
    omme
    0.38
     úpl
    0.36
    ativo
    0.36
    弛
    0.35
    ملك
    0.35
     Latter
    0.35
     cervello
    0.34
     cev
    0.34
    Activations Density 0.009%

    No Known Activations