© 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. 207799
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     podle
    0.38
     crédit
    0.38
    rani
    0.37
    minim
    0.36
    ńskie
    0.36
    天赋
    0.36
    勢
    0.36
     kredi
    0.36
     enligt
    0.35
    盼
    0.34
    POSITIVE LOGITS
     Kuala
    0.41
     Dallas
    0.41
     Business
    0.40
     Istanbul
    0.40
     дело
    0.39
     Advanced
    0.39
     casc
    0.39
     Active
    0.38
     Islamabad
    0.38
     Andreas
    0.38
    Activations Density 0.000%

    No Known Activations