© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175531
    Prev
    Next
    INDEX
    Explanations

    wider open

    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_50_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
     K
    0.73
     الك
    0.53
    K
    0.52
     k
    0.50
     К
    0.48
     Techno
    0.48
     Techn
    0.47
     Lif
    0.47
     TAC
    0.46
     Life
    0.46
    POSITIVE LOGITS
     З
    0.38
     ov
    0.38
     blanches
    0.37
     Z
    0.37
     privacy
    0.37
    جز
    0.35
     φω
    0.35
    хой
    0.35
     spend
    0.35
     ब्रै
    0.35
    Activations Density 0.046%

    No Known Activations