© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35108
    Prev
    Next
    INDEX
    Explanations

    Introductory / pmod

    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_7_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
     způ
    1.05
    䀠
    0.94
    Detectable
    0.90
     kawaida
    0.89
    の
    0.89
    のス
    0.88
    晧
    0.88
     asalamualaikum
    0.87
    했어요
    0.87
     osobe
    0.86
    POSITIVE LOGITS
    t
    0.86
    you
    0.86
    ↵
    0.83
    ।
    0.79
    ,
    0.76
    chi
    0.75
     Tổng
    0.71
    ও
    0.71
     (!)
    0.70
    bar
    0.70
    Activations Density 0.000%

    No Known Activations