© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212643
    Prev
    Next
    INDEX
    Explanations

    embodies characteristics or qualities

    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
     to
    1.80
    in
    1.62
    to
    1.62
    u
    1.59
     is
    1.45
    ق
    1.35
    ic
    1.17
    iv
    1.11
    c
    1.10
    да
    1.08
    POSITIVE LOGITS
    。
    1.15
    이다
    1.01
    (
    1.00
    ।
    0.99
    ।)
    0.95
    ।]
    0.91
    ِ
    0.91
    </strong>
    0.89
    ។
    0.89
    นิ
    0.88
    Activations Density 0.001%

    No Known Activations