© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47834
    Prev
    Next
    INDEX
    Explanations

    like-minded people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    ’
    1.02
    Кроме
    0.82
     Inoltre
    0.80
     nécessaires
    0.78
    Эти
    0.77
    Ⲏ
    0.77
     Andere
    0.77
    تر
    0.76
     tekrar
    0.75
     Apare
    0.75
    POSITIVE LOGITS
     network
    0.75
    ↵
    0.73
     software
    0.70
     virtualization
    0.70
     callable
    0.69
     riparian
    0.69
      
    0.68
     ripple
    0.68
    ming
    0.67
     desktop
    0.66
    Activations Density 0.001%

    No Known Activations