© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67320
    Prev
    Next
    INDEX
    Explanations

    theme

    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_46_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
     V
    0.43
     Boca
    0.40
    ത്രം
    0.39
     смы
    0.38
     प्रत्यक्ष
    0.38
     DIN
    0.37
     Dich
    0.37
     M
    0.37
     Ping
    0.37
     Creed
    0.37
    POSITIVE LOGITS
    themes
    0.51
    Themes
    0.45
     Theme
    0.44
     theme
    0.44
     themes
    0.43
     themed
    0.43
     Themes
    0.42
    Theme
    0.41
    theme
    0.40
    omètre
    0.38
    Activations Density 0.001%

    No Known Activations