© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202887
    Prev
    Next
    INDEX
    Explanations

    world

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     ответственность
    0.43
     NIE
    0.41
     તૈય
    0.40
     আঙ
    0.40
     Nie
    0.39
     Paragon
    0.38
    莞
    0.38
     toes
    0.38
     nip
    0.37
    ्ले
    0.37
    POSITIVE LOGITS
     ذه
    0.45
    BUF
    0.42
    ǀ
    0.42
    Wise
    0.41
     wildly
    0.39
    رسٹ
    0.39
    wise
    0.38
    getBook
    0.37
    貿易
    0.37
     awoke
    0.37
    Activations Density 0.001%

    No Known Activations