© 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. 236918
    Prev
    Next
    INDEX
    Explanations

    word parts

    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
     brachial
    0.46
    鲑
    0.43
     Shepard
    0.42
    大量
    0.40
     biographies
    0.40
     Faculty
    0.38
     Brigham
    0.38
     Sheldon
    0.38
    ланти
    0.37
    浊
    0.37
    POSITIVE LOGITS
     Oyo
    0.42
    umsi
    0.41
     depreci
    0.41
     मैनु
    0.40
    सो
    0.40
     codewords
    0.39
     뭐
    0.39
     kode
    0.39
     ಬ್ಯಾ
    0.39
    õ
    0.38
    Activations Density 0.000%

    No Known Activations