© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38933
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ат
    1.06
     ат
    1.05
    AT
    1.03
    <0x81>
    1.02
    АТ
    1.02
     Atkins
    1.01
     Atkinson
    0.98
     ATC
    0.97
     ات
    0.96
     Atwood
    0.94
    POSITIVE LOGITS
    𝚝
    0.84
    ᴛ
    0.81
    ты
    0.77
    ﺘ
    0.77
    ْت
    0.76
    𝙩
    0.75
    T
    0.75
    т
    0.75
    𝔱
    0.75
    𝖙
    0.75
    Activations Density 0.011%

    No Known Activations