© 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. 129069
    Prev
    Next
    INDEX
    Explanations

    congo

    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
    б
    1.15
     razones
    1.07
    b
    1.05
     завер
    1.01
    ل
    1.01
     роди
    0.99
    d
    0.99
     дав
    0.98
    al
    0.98
    ：
    0.93
    POSITIVE LOGITS
    ING
    1.80
    لی
    1.45
    ী
    1.45
    я
    1.36
    ת
    1.34
    个
    1.29
    ة
    1.28
    い
    1.24
    ை
    1.24
    า
    1.23
    Activations Density 0.000%

    No Known Activations