© 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. 25011
    Prev
    Next
    INDEX
    Explanations

    and

    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
     supplies
    0.44
    Dis
    0.40
     RN
    0.40
     Supplies
    0.40
     Dis
    0.40
     under
    0.40
    \}.
    0.39
     dis
    0.38
     डिस्क
    0.38
     Supply
    0.38
    POSITIVE LOGITS
    έ
    0.40
    বাচক
    0.39
     devrait
    0.39
    ര്‍ട്ട്
    0.38
    ˹
    0.38
     τὸ
    0.38
    OfType
    0.37
     చిత
    0.37
    ARRAY
    0.37
    wegs
    0.37
    Activations Density 0.000%

    No Known Activations