© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130574
    Prev
    Next
    INDEX
    Explanations

    conscious evolution themes

    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
     Preferred
    0.44
     V
    0.42
     آہ
    0.38
    ਾਮ
    0.38
    usa
    0.37
    aliya
    0.37
     Mish
    0.37
    ラム
    0.36
    टू
    0.36
     OB
    0.36
    POSITIVE LOGITS
     gust
    0.38
    gres
    0.37
    𝘨
    0.37
    metto
    0.37
     способности
    0.36
    ⏎
    0.36
     hop
    0.36
    ShoppingCart
    0.35
    畋
    0.35
     ability
    0.33
    Activations Density 0.028%

    No Known Activations