© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1855
    Prev
    Next
    INDEX
    Explanations

    hands-on

    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_40_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
     وړاندوینې
    0.36
    OPENJDK
    0.36
     युवाओ
    0.35
     adventures
    0.35
    伀
    0.35
    oplayer
    0.34
    rese
    0.34
     অবজারভার
    0.34
    𐰆
    0.34
     மறை
    0.33
    POSITIVE LOGITS
     esp
    0.37
     ch
    0.36
    getPosition
    0.35
     लोड
    0.34
     reload
    0.34
     قلب
    0.34
     landing
    0.33
     ova
    0.33
    )|\
    0.33
    ロード
    0.33
    Activations Density 0.009%

    No Known Activations