© 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. 248019
    Prev
    Next
    INDEX
    Explanations

    legal / formal documents

    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
     having
    0.82
     Having
    0.74
    Having
    0.72
     HAVING
    0.71
    having
    0.70
     ayant
    0.58
     tendo
    0.58
     namely
    0.53
    namely
    0.52
    --
    0.47
    POSITIVE LOGITS
    кторов
    0.43
    ೀರ
    0.40
     prays
    0.40
    yards
    0.39
     конститу
    0.39
     ارب
    0.38
     ಮುಂದೆ
    0.38
     diyor
    0.37
    amanya
    0.37
     corrispond
    0.37
    Activations Density 0.000%

    No Known Activations