© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50408
    Prev
    Next
    INDEX
    Explanations

    subtitle

    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_31_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
     ڈیٹا
    0.40
    セックス
    0.39
     रोज
    0.37
    リーチ
    0.37
     diketahui
    0.36
    setupUi
    0.35
    自行
    0.35
    衩
    0.35
    Hm
    0.35
    ERIC
    0.34
    POSITIVE LOGITS
    ikkh
    0.37
     activated
    0.36
     baryons
    0.35
     ‘
    0.35
    ப்பட்டுள்ளது
    0.35
     unavoid
    0.35
     saddle
    0.35
     കമ
    0.35
     various
    0.34
    困难
    0.34
    Activations Density 0.004%

    No Known Activations