© 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. 137104
    Prev
    Next
    INDEX
    Explanations

    brands and listings

    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
     cl
    0.44
     фрон
    0.41
    xtures
    0.40
    ષા
    0.39
    mocks
    0.39
    ocr
    0.39
    eas
    0.39
    垻
    0.39
     mocks
    0.38
    pathy
    0.38
    POSITIVE LOGITS
    त्सा
    0.44
    Dup
    0.43
    Fuj
    0.40
    Prima
    0.40
     Prima
    0.39
     prostor
    0.39
     bén
    0.38
     fdata
    0.37
    %%%%%%%%
    0.36
    ᥙ
    0.36
    Activations Density 0.001%

    No Known Activations