© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153514
    Prev
    Next
    INDEX
    Explanations

    why even

    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_23_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
    ‏‏
    0.29
     Invent
    0.24
     있었다
    0.23
     Targeting
    0.22
    vió
    0.22
    ‏
    0.22
     রহিয়াছে
    0.22
     பொறு
    0.22
    র্ডার
    0.22
     Lanes
    0.22
    POSITIVE LOGITS
     Keaton
    0.26
    лата
    0.25
     shiny
    0.24
    忔
    0.23
     dirty
    0.23
     intrat
    0.23
    ,&
    0.23
    Dirt
    0.23
     quilt
    0.23
    )».
    0.23
    Activations Density 0.007%

    No Known Activations