© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228957
    Prev
    Next
    INDEX
    Explanations

    disapprove

    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_6_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
    ids
    1.07
    (
    0.99
    ها
    0.99
    iden
    0.96
    abel
    0.96
    ometers
    0.95
    س
    0.95
    ien
    0.93
    ella
    0.91
    de
    0.89
    POSITIVE LOGITS
    t
    1.13
     socialize
    1.03
    すでに
    1.02
    ﺔ
    0.98
    𝓽
    0.98
     quiver
    0.96
    ড
    0.96
     impede
    0.95
     yaptı
    0.94
     fonksiyon
    0.94
    Activations Density 0.001%

    No Known Activations