© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159660
    Prev
    Next
    INDEX
    Explanations

    ocia, ox, coc, Ock, Koxinga

    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_2_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
    ure
    1.09
    ่
    0.98
    ี
    0.93
    ில்
    0.93
    й
    0.93
    ъ
    0.92
    esh
    0.87
    oltre
    0.87
    í
    0.86
     ולה
    0.85
    POSITIVE LOGITS
    ا
    1.31
    ם
    1.28
    is
    1.23
    리
    1.19
     is
    1.17
    기
    1.16
    다
    1.13
    是
    1.12
    ق
    1.09
    ל
    1.08
    Activations Density 0.000%

    No Known Activations