© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203622
    Prev
    Next
    INDEX
    Explanations

    opposition / oposiciones

    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
    en
    0.97
    :
    0.96
    es
    0.93
    ين
    0.89
    м
    0.89
    ي
    0.88
     في
    0.88
    يلا
    0.86
    માં
    0.86
    ulare
    0.85
    POSITIVE LOGITS
    )\
    1.06
     you
    1.05
     =
    0.96
     to
    0.91
    )$.
    0.91
     or
    0.88
    )$
    0.84
    सुद्धा
    0.84
    O
    0.82
    คุณ
    0.77
    Activations Density 0.000%

    No Known Activations