© 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. 110348
    Prev
    Next
    INDEX
    Explanations

    drastically different or reduced

    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
     as
    1.49
    ↵
    1.02
    ட
    1.00
     lanjut
    0.97
    ল
    0.95
    ス
    0.93
    AK
    0.93
    ので
    0.92
    dauer
    0.91
    ിയ
    0.90
    POSITIVE LOGITS
    y
    1.59
    b
    1.17
    é
    1.17
    ى
    1.13
    c
    1.01
    até
    0.98
    는
    0.98
    ij
    0.96
    in
    0.96
     всё
    0.96
    Activations Density 0.002%

    No Known Activations