© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161557
    Prev
    Next
    INDEX
    Explanations

    MAID, lenni

    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
    '
    1.61
    d
    1.39
    dır
    1.28
    ব
    1.28
    )
    1.27
    n
    1.24
    मध्ये
    1.23
    ง
    1.21
    ),
    1.16
    ')
    1.15
    POSITIVE LOGITS
     في
    1.16
    很
    0.99
     لي
    0.89
    ጇ
    0.88
     ني
    0.87
    يفة
    0.86
     البي
    0.85
    喵
    0.84
    8
    0.83
     تاريخ
    0.83
    Activations Density 0.000%

    No Known Activations