© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9407
    Prev
    Next
    INDEX
    Explanations

    contracting opportunities for minority-owned businesses

    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_13_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
    
    0.44
    さ
    0.44
    জমেন্ট
    0.43
    Fusion
    0.43
     communautés
    0.43
    ます
    0.42
    ств
    0.42
     insofar
    0.41
    пан
    0.41
    𝑆
    0.41
    POSITIVE LOGITS
    iai
    0.57
     ه
    0.50
     Rodr
    0.49
     நாக
    0.49
     Hulk
    0.48
     Pikachu
    0.48
     Car
    0.47
     हफ्ते
    0.47
     Rodney
    0.46
     величи
    0.46
    Activations Density 0.021%

    No Known Activations