© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90287
    Prev
    Next
    INDEX
    Explanations

    3

    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_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     و
    0.44
     ...
    0.43
     “…
    0.43
     The
    0.43
     They
    0.42
     الاست
    0.42
      
    0.41
     "...
    0.40
    …
    0.40
     This
    0.40
    POSITIVE LOGITS
    4
    0.72
    5
    0.72
    ４
    0.64
    ४
    0.63
    ५
    0.60
    ۵
    0.60
    ５
    0.57
    ٤
    0.57
    
    0.56
    7
    0.56
    Activations Density 0.003%

    No Known Activations