© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38941
    Prev
    Next
    INDEX
    Explanations

    Arabic step

    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_57_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
     مض
    0.44
     إن
    0.43
     ин
    0.40
     أخ
    0.39
     مش
    0.37
     المش
    0.36
    إن
    0.35
    候
    0.35
     بر
    0.35
     broadband
    0.35
    POSITIVE LOGITS
     Nuk
    0.39
     توا
    0.38
    凝
    0.37
     W
    0.36
     McNeil
    0.36
     للمع
    0.35
     Hagg
    0.35
     Nak
    0.35
     Pich
    0.35
     రే
    0.34
    Activations Density 0.000%

    No Known Activations