© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 233095
    Prev
    Next
    INDEX
    Explanations

    regulatory, economic, financial environment

    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_6_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
    1.01
    ल
    0.89
    ะ
    0.84
    ns
    0.82
    us
    0.81
     Kabupaten
    0.81
    ss
    0.80
    rt
    0.80
    isers
    0.80
     regions
    0.79
    POSITIVE LOGITS
    AR
    0.96
    Y
    0.96
    الية
    0.90
    O
    0.86
     confortável
    0.86
    وسي
    0.83
    时间的
    0.83
     jeopard
    0.79
    Q
    0.78
    вина
    0.78
    Activations Density 0.002%

    No Known Activations