© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69476
    Prev
    Next
    INDEX
    Explanations

    previously

    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_46_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
    过的
    1.85
    過的
    1.85
    过
    1.77
    過
    1.70
     over
    1.68
    過了
    1.52
    过了
    1.48
     過
    1.32
     Over
    1.23
     过
    1.22
    POSITIVE LOGITS
    Previously
    0.49
     previously
    0.44
     Previously
    0.43
     vorige
    0.43
    previously
    0.41
    itespace
    0.38
     tidigare
    0.38
     поперед
    0.38
    apparently
    0.38
     предыду
    0.36
    Activations Density 0.007%

    No Known Activations