© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8158
    Prev
    Next
    INDEX
    Explanations

    can I / we

    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_40_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
    Nuestro
    0.47
     Nuestros
    0.45
     možete
    0.43
     Our
    0.43
    Unsere
    0.42
     môžu
    0.42
    呥
    0.41
    我が
    0.40
    ebilirsiniz
    0.40
    Our
    0.40
    POSITIVE LOGITS
     we
    1.48
     мы
    1.33
     हम
    1.19
     আমরা
    1.16
    我们
    1.05
     chúng
    1.05
     ہم
    1.04
    我們
    0.96
     우리는
    0.95
    we
    0.92
    Activations Density 0.410%

    No Known Activations