© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110554
    Prev
    Next
    INDEX
    Explanations

    humorously

    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_2_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
    т
    1.31
    на
    1.19
    ان
    1.14
    צ
    1.11
    ва
    1.09
    ت
    1.07
    ung
    1.03
    та
    1.03
    мі
    1.01
    к
    1.01
    POSITIVE LOGITS
     to
    1.21
    1.13
    것
    1.12
    있
    1.11
    RE
    1.07
    ए
    0.98
    多い
    0.96
    กัน
    0.91
     silos
    0.89
     tokamaks
    0.89
    Activations Density 0.000%

    No Known Activations