© 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. 159825
    Prev
    Next
    INDEX
    Explanations

    breathable materials

    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
     for
    1.34
    ൻ
    1.24
    for
    1.15
    b
    1.14
     a
    1.12
    م
    1.09
    TRA
    1.05
    ত
    1.04
    id
    1.02
    the
    1.00
    POSITIVE LOGITS
    ного
    1.23
    เป็น
    1.11
    在
    1.04
    ನ
    1.04
    อน
    1.03
    ุ
    1.02
    ное
    1.01
    ят
    0.97
    ном
    0.95
    จะ
    0.93
    Activations Density 0.000%

    No Known Activations