© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213648
    Prev
    Next
    INDEX
    Explanations

    nanoparticles, article

    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_5_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
     on
    1.34
     are
    1.23
    ק
    1.13
    ൈ
    1.11
    ى
    1.08
     airline
    1.02
     &
    0.99
     incineration
    0.99
     il
    0.98
     arte
    0.97
    POSITIVE LOGITS
    ра
    1.48
    ح
    1.43
    وا
    1.34
    the
    1.30
    У
    1.28
    場合
    1.26
    otipi
    1.22
    인
    1.18
    for
    1.17
     Și
    1.16
    Activations Density 0.000%

    No Known Activations