© 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. 171010
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    ％
    0.36
    铱
    0.36
    wohn
    0.36
    
    0.35
     तोड़
    0.35
    医
    0.35
    옻
    0.35
    .​
    0.35
    rité
    0.34
    ల్లో
    0.34
    POSITIVE LOGITS
     US
    0.44
     "^
    0.42
     payers
    0.42
     paying
    0.42
     "$"
    0.40
     mutter
    0.40
     base
    0.39
     api
    0.39
     converters
    0.39
     Laj
    0.39
    Activations Density 0.002%

    No Known Activations