© 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. 88861
    Prev
    Next
    INDEX
    Explanations

    immune system attacks or overreacts

    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
    Warner
    0.40
    McL
    0.39
     MI
    0.38
     Warner
    0.38
    ائب
    0.38
    INE
    0.38
     Thunderbird
    0.38
    阿
    0.38
     Group
    0.37
    在一
    0.37
    POSITIVE LOGITS
    пита
    0.40
     übrig
    0.39
     fürs
    0.39
    荖
    0.39
    чита
    0.38
     இருந்தாலும்
    0.38
     zichzelf
    0.38
     بونس
    0.38
    溸
    0.38
     leftover
    0.37
    Activations Density 0.010%

    No Known Activations