© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 79725
    Prev
    Next
    INDEX
    Explanations

    be realistic honest

    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_29_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
    𝖆
    0.41
    ⴹ
    0.39
    挥
    0.37
    Лю
    0.35
    一体
    0.35
     Лю
    0.34
     civilizations
    0.33
    苍
    0.33
     nech
    0.33
     hert
    0.33
    POSITIVE LOGITS
    I
    0.38
     quarters
    0.37
     I
    0.36
     শরণ
    0.36
    test
    0.36
     breakouts
    0.35
     test
    0.35
    suggestions
    0.35
    TERS
    0.34
    対訳
    0.34
    Activations Density 0.012%

    No Known Activations